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

    Neuronpedia

    INDEX
    Explanations

    common topics or agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gallery
    -0.67
    pload
    -0.67
    igil
    -0.66
     Uriel
    -0.66
     Laksh
    -0.63
     Colts
    -0.62
    unknown
    -0.60
     lantern
    -0.60
     predators
    -0.59
     temples
    -0.59
    POSITIVE LOGITS
    iqueness
    0.89
     principle
    0.81
     unanimously
    0.79
     agreeing
    0.77
     terms
    0.74
     dogma
    0.73
    incerity
    0.71
    heartedly
    0.69
    ensical
    0.67
    iatus
    0.67
    Act Density 0.197%

    No Known Activations