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

    Neuronpedia

    INDEX
    Explanations

    keywords related to actions or events that have significant consequences or impact

    oai_token-act-pair · gpt-3.5-turbo

    temporal markers and conditions associated with ongoing situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.76
    etheless
    -0.71
    VERTISEMENT
    -0.68
    ailability
    -0.66
     conflic
    -0.58
    erent
    -0.55
    ranean
    -0.54
    natureconservancy
    -0.54
    âĸ¬
    -0.54
    retty
    -0.54
    POSITIVE LOGITS
     to
    1.04
     and
    0.82
    :
    0.78
    to
    0.75
     To
    0.73
    ;
    0.73
    ,
    0.69
     for
    0.67
     because
    0.66
     –
    0.66
    Act Density 0.717%

    No Known Activations