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

    Neuronpedia

    INDEX
    Explanations

    references to organizations or events, particularly the "Forum"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Forum" as a significant entity or subject in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meter
    -0.68
    teenth
    -0.67
    STON
    -0.65
    kowski
    -0.63
    stroke
    -0.63
    lys
    -0.62
    ymes
    -0.62
    birds
    -0.61
    adding
    -0.61
    mia
    -0.60
    POSITIVE LOGITS
    edIn
    0.80
     Forum
    0.78
    ioned
    0.76
    ilitation
    0.76
    naire
    0.73
    ãĥ¼ãĥĨãĤ£
    0.71
    area
    0.66
    atorium
    0.65
    rade
    0.65
    urion
    0.65
    Act Density 0.013%

    No Known Activations