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

    Neuronpedia

    INDEX
    Explanations

    keywords signaling the reader to read additional content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "READ" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phi
    -0.66
    angel
    -0.66
    asketball
    -0.66
    afort
    -0.64
    oteric
    -0.64
    unity
    -0.64
    basketball
    -0.63
    ugi
    -0.63
    aviour
    -0.62
    venge
    -0.61
    POSITIVE LOGITS
    READ
    1.02
     aloud
    0.99
     READ
    0.94
     ALSO
    0.91
    MORE
    0.88
     WRITE
    0.84
     WATCHED
    0.83
    NESS
    0.82
     MORE
    0.82
    TY
    0.81
    Act Density 0.006%

    No Known Activations