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

    Neuronpedia

    INDEX
    Explanations

    words related to emotional or surprising reactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     slips
    -0.66
    nect
    -0.65
    uben
    -0.63
    illusion
    -0.63
    omo
    -0.63
    itamin
    -0.61
    spring
    -0.61
    pleted
    -0.61
     forearm
    -0.60
     annexed
    -0.60
    POSITIVE LOGITS
     me
    1.02
     onlook
    1.01
     us
    0.97
    ingly
    0.96
     him
    0.83
     commenters
    0.81
     audiences
    0.78
     investigators
    0.78
     reviewers
    0.77
     readers
    0.76
    Act Density 0.110%

    No Known Activations