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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.91
    Ùĩ
    -0.50
    ska
    -0.39
    a
    -0.36
    sburg
    -0.36
    sar
    -0.32
    sand
    -0.31
    sik
    -0.31
    न
    -0.30
    sian
    -0.29
    POSITIVE LOGITS
    odore
    0.31
    atre
    0.28
    ÑįÑĤомÑĥ
    0.24
    etheless
    0.23
    adays
    0.23
    imately
    0.20
    gether
    0.20
    quarters
    0.19
    tlement
    0.19
    bsites
    0.19
    Act Density 0.287%

    No Known Activations