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

    Neuronpedia

    INDEX
    Explanations

    recent events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.68
     seiz
    -0.67
     manifold
    -0.66
     cous
    -0.65
     challeng
    -0.65
    risk
    -0.63
     Pattern
    -0.60
     attendant
    -0.59
    chwitz
    -0.58
    anon
    -0.57
    POSITIVE LOGITS
    ifiable
    1.10
    ifications
    1.06
    itia
    0.92
    IFIED
    0.91
    ifi
    0.88
    IFIC
    0.86
    if
    0.80
    ifiers
    0.77
     shy
    0.77
     WATCHED
    0.75
    Act Density 0.072%

    No Known Activations