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

    Neuronpedia

    INDEX
    Explanations

    countries and proper nouns related to different geographical regions

    oai_token-act-pair · gpt-3.5-turbo

    references to Solomon and associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ultras
    -0.83
    glas
    -0.77
     Certified
    -0.68
     ticks
    -0.67
    TS
    -0.67
     gest
    -0.67
    hend
    -0.66
    oglobin
    -0.65
    hai
    -0.65
    Buff
    -0.65
    POSITIVE LOGITS
     Solomon
    3.33
     Saul
    1.65
    Sol
    1.23
    omon
    1.16
     Pit
    1.09
    atorial
    1.05
     Lazarus
    1.04
     Paradise
    1.02
     Liberty
    0.94
     Kor
    0.93
    Act Density 0.036%

    No Known Activations