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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with functions and programming elements

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

    111 followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſicht
    -0.88
    ⟬
    -0.87
    ſehen
    -0.85
    iſche
    -0.82
    ロウィン
    -0.81
    niſſe
    -0.81
    Espèce
    -0.81
    adaptiveStyles
    -0.81
    iſchen
    -0.80
    iſen
    -0.80
    POSITIVE LOGITS
     majority
    0.59
    1
    0.40
    -
    0.39
     SSS
    0.39
    //
    0.38
    AAA
    0.38
    3
    0.38
    pp
    0.37
    ccc
    0.36
     CCC
    0.36
    Act Density 0.052%

    No Known Activations