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

    Neuronpedia

    INDEX
    Explanations

    characters in a script played by specific actors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating who is playing the characters in a film or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cair
    -0.87
    ousse
    -0.87
    bia
    -0.85
    teness
    -0.79
    bard
    -0.77
    iscal
    -0.77
    idation
    -0.77
    sels
    -0.76
    ptoms
    -0.75
    eah
    -0.75
    POSITIVE LOGITS
     Kev
    0.83
    pass
    0.80
     Tony
    0.80
     Jeffrey
    0.79
     Natalie
    0.78
     Ken
    0.78
     Mari
    0.77
     Josh
    0.75
     virtue
    0.75
     Jonathan
    0.74
    Act Density 0.086%

    No Known Activations