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

    Neuronpedia

    INDEX
    Explanations

    parentheses with a numerical value inside

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.82
     behavi
    -0.75
    CLASSIFIED
    -0.73
    ¬¼
    -0.68
    GoldMagikarp
    -0.67
    Magikarp
    -0.64
     corrid
    -0.63
     exha
    -0.62
    vous
    -0.62
    kefeller
    -0.61
    POSITIVE LOGITS
     (
    2.04
     ("
    1.72
     ([
    1.66
     ('
    1.61
     (~
    1.57
     (-
    1.53
     (<
    1.52
     ((
    1.51
     (.
    1.50
     (=
    1.49
    Act Density 0.195%

    No Known Activations