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

    Neuronpedia

    INDEX
    Explanations

    mentions of the acronym "CH" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific sports league or team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.86
    ãĥĥãĥī
    -0.83
    sov
    -0.77
    ãĤ´ãĥ³
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.75
    gency
    -0.70
    gaard
    -0.68
    fitting
    -0.68
    Äį
    -0.68
    glass
    -0.66
    POSITIVE LOGITS
    APTER
    1.13
    ECK
    1.06
    OOL
    0.98
    ANGE
    0.97
    apeake
    0.97
    ANN
    0.95
    OME
    0.91
    AIR
    0.90
    ivalry
    0.89
    ILD
    0.89
    Act Density 0.015%

    No Known Activations