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

    Neuronpedia

    INDEX
    Explanations

    newsletters as a topic of interest or importance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Pixie
    -0.70
     tatt
    -0.67
    total
    -0.66
     onwards
    -0.66
     studied
    -0.65
    ogram
    -0.65
     griev
    -0.64
    typ
    -0.64
    whelming
    -0.64
    past
    -0.64
    POSITIVE LOGITS
    CHAT
    0.84
    LOCK
    0.79
    Malley
    0.76
    BLIC
    0.75
    icro
    0.75
    avi
    0.73
     Annotations
    0.73
    insula
    0.73
    Streamer
    0.72
    enaries
    0.72
    Act Density 0.093%

    No Known Activations