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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to artistic works or projects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fecture
    -0.78
    PLIED
    -0.73
    enegger
    -0.68
    enance
    -0.68
     administr
    -0.67
     claimants
    -0.67
     jurisd
    -0.65
    stration
    -0.65
    lished
    -0.64
     vested
    -0.64
    POSITIVE LOGITS
     Girl
    0.92
     Circus
    0.85
     Fever
    0.84
     Mortal
    0.84
     Velvet
    0.83
     Tomorrow
    0.83
     Dance
    0.83
     Night
    0.83
     Days
    0.82
     Stranger
    0.81
    Act Density 0.462%

    No Known Activations