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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food and drinks

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks that denote the conclusion of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retracted
    -0.78
     exit
    -0.77
     extinguished
    -0.77
     rupture
    -0.73
     sacked
    -0.73
     displaced
    -0.73
     resc
    -0.71
     attrition
    -0.70
     accuser
    -0.70
     casualty
    -0.70
    POSITIVE LOGITS
     Anyway
    1.55
    Anyway
    1.47
     Needless
    1.40
     Recently
    1.32
     Personally
    1.30
     Therefore
    1.24
     However
    1.21
     Unfortunately
    1.20
     Basically
    1.20
     Interestingly
    1.20
    Act Density 0.564%

    No Known Activations