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

    Neuronpedia

    INDEX
    Explanations

    dates in the format MM/DD/YYYY

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or series of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govern
    -0.69
    stories
    -0.69
    interstitial
    -0.68
    selves
    -0.67
    agine
    -0.67
    gow
    -0.66
    estate
    -0.64
    PIN
    -0.64
    gress
    -0.64
    !:
    -0.63
    POSITIVE LOGITS
     huh
    0.91
     etc
    0.81
     ?)
    0.73
     supra
    0.72
     eh
    0.71
     LLC
    0.67
    000
    0.67
     Jr
    0.65
    048
    0.65
     Pt
    0.65
    Act Density 0.205%

    No Known Activations