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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing states of being or activities

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions and responses to experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    habi
    -0.78
    ctuary
    -0.75
    hovah
    -0.67
    osponsors
    -0.67
    tains
    -0.66
    ocumented
    -0.64
    itutes
    -0.61
    scribe
    -0.60
    ividual
    -0.59
    ocument
    -0.57
    POSITIVE LOGITS
     hadn
    0.70
    Was
    0.68
     calmed
    0.64
     inval
    0.63
     hurried
    0.62
     rushed
    0.61
     didn
    0.61
    went
    0.60
     Turns
    0.60
     felt
    0.60
    Act Density 1.598%

    No Known Activations