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

    Neuronpedia

    INDEX
    Explanations

    expressions related to family relationships

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that denote qualities or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.89
    ãĥ¯ãĥ³
    -0.88
    igent
    -0.80
    href
    -0.80
    itect
    -0.77
     Gutenberg
    -0.75
    iguous
    -0.74
    ileaks
    -0.74
    rawdownloadcloneembedreportprint
    -0.73
    ADRA
    -0.72
    POSITIVE LOGITS
    puff
    1.01
    tics
    0.95
    rics
    0.79
    pha
    0.79
    ffe
    0.76
    zed
    0.73
    cemic
    0.71
     slopes
    0.69
    cos
    0.68
    tons
    0.67
    Act Density 0.035%

    No Known Activations