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

    Neuronpedia

    INDEX
    Explanations

    instances of strong reactions to events or stimuli

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    holder
    -1.15
    iciency
    -1.01
    hold
    -1.00
    skip
    -0.89
    locked
    -0.86
    holding
    -0.85
    estones
    -0.83
    feat
    -0.82
    score
    -0.80
    fusc
    -0.79
    POSITIVE LOGITS
    ivated
    1.75
    aries
    1.61
    ivating
    1.56
    ivation
    1.54
     reaction
    1.39
     reactions
    1.35
    ively
    1.22
     Reaction
    1.21
    uating
    1.16
    ary
    1.11
    Act Density 1.244%

    No Known Activations