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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, legal matters, and news events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    holders
    -0.82
    holder
    -0.73
     deed
    -0.72
    erest
    -0.63
    ean
    -0.63
    vier
    -0.62
    ipeg
    -0.61
     farmer
    -0.61
    elta
    -0.61
     Hurricanes
    -0.60
    POSITIVE LOGITS
    active
    1.06
     Shack
    0.89
    ode
    0.83
    angelo
    0.81
    Radio
    0.80
    omatic
    0.78
    algia
    0.77
     Songs
    0.77
    oute
    0.74
    Plex
    0.74
    Act Density 5.503%

    No Known Activations