Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure, particularly parentheses, data types, and table creation statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or mathematical expressions containing parentheses and numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers inside parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.51
    zeiti
    -0.28
    posób
    -0.27
     Geraadpleegd
    -0.27
    得上
    -0.27
     insuffisamment
    -0.27
     Weise
    -0.26
     нужда
    -0.26
     跳转至
    -0.25
     vyb
    -0.24
    POSITIVE LOGITS
    extAlignment
    0.66
     $_(
    0.63
     XNUMX
    0.61
     $_-
    0.57
    ConstraintMaker
    0.56
    ſſung
    0.56
     насељу
    0.56
    <unused41>
    0.55
    [@BOS@]
    0.55
    <unused3>
    0.55
    Act Density 1.629%

    No Known Activations