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

    Neuronpedia

    INDEX
    Explanations

    words related to reactions and responses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reaction" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hold
    -0.74
     Sinai
    -0.74
    holder
    -0.73
    iciency
    -0.71
    locked
    -0.66
    fficiency
    -0.62
    enture
    -0.61
    cipled
    -0.60
    red
    -0.60
    soDeliveryDate
    -0.59
    POSITIVE LOGITS
    ivated
    1.25
     reactions
    1.17
    aries
    1.14
     reaction
    1.13
    ivating
    1.10
    ivation
    1.08
     Reaction
    1.04
     negatively
    0.87
    iv
    0.86
     thereto
    0.82
    Act Density 0.033%

    No Known Activations