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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.77
    ocument
    -0.71
    resa
    -0.69
    ifference
    -0.67
    amaz
    -0.66
     AST
    -0.59
    agonal
    -0.59
    river
    -0.59
    heny
    -0.59
    acters
    -0.59
    POSITIVE LOGITS
     termed
    1.14
     dubbed
    1.14
     nicknamed
    1.05
     deems
    0.98
     deemed
    0.97
     promptly
    0.97
     dub
    0.96
     deem
    0.95
     euphem
    0.93
     duly
    0.93
    Act Density 0.142%

    No Known Activations