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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to political figures and appointments

    oai_token-act-pair · gpt-3.5-turbo

    names and titles associated with political appointments and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deterioration
    -0.61
    ecd
    -0.60
     difference
    -0.58
     maze
    -0.58
     wob
    -0.58
    ggles
    -0.57
     satur
    -0.57
     observable
    -0.55
     sense
    -0.55
    vine
    -0.55
    POSITIVE LOGITS
     to
    0.79
     onto
    0.79
     into
    0.78
     honorary
    0.75
     anew
    0.73
     nomination
    0.73
    into
    0.73
     accordingly
    0.72
     alongside
    0.70
    Guest
    0.68
    Act Density 0.484%

    No Known Activations