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

    Neuronpedia

    INDEX
    Explanations

    references to statistical models and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cristo
    -0.64
     ролях
    -0.61
     snip
    -0.59
     tears
    -0.56
    שלום
    -0.54
    fromnode
    -0.53
    SUV
    -0.52
     Reiss
    -0.52
    ffindor
    -0.51
    blis
    -0.51
    POSITIVE LOGITS
    存于互联网档案馆
    1.04
     تانيه
    0.77
     lever
    0.64
    Cyclic
    0.63
    AndEndTag
    0.61
    ValueStyle
    0.59
    bull
    0.59
    $_['
    0.58
     Rota
    0.58
    rot
    0.57
    Act Density 2.322%

    No Known Activations