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

    Neuronpedia

    INDEX
    Explanations

    words related to various reactions or responses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to responses and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciency
    -0.82
    friends
    -0.74
    cipled
    -0.68
    lay
    -0.67
    holder
    -0.66
    fusc
    -0.65
     Hels
    -0.65
    scribe
    -0.62
     Sinai
    -0.61
    locked
    -0.60
    POSITIVE LOGITS
    ivated
    1.31
    aries
    1.20
    ivating
    1.19
    ivation
    1.12
     reactions
    1.06
     reaction
    1.03
     thereto
    0.92
     Reaction
    0.88
     negatively
    0.86
    ivity
    0.85
    Act Density 0.035%

    No Known Activations