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

    Neuronpedia

    INDEX
    Explanations

    numeric codes or abbreviations related to specific organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "CH" followed by a number, indicating a specific classification, category, or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.78
    ãĥĥãĥī
    -0.76
    sov
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.73
    gency
    -0.72
    ãĤ´ãĥ³
    -0.71
    gaard
    -0.70
    Äĩ
    -0.67
    ¯¯¯¯
    -0.67
     belt
    -0.66
    POSITIVE LOGITS
    APTER
    1.06
    ECK
    1.03
    ANGE
    0.99
    ANN
    0.98
    OOL
    0.96
    OME
    0.95
    ivalry
    0.94
    apeake
    0.93
    ILD
    0.88
    AIN
    0.88
    Act Density 0.017%

    No Known Activations