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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samoa
    -0.94
     Staten
    -0.90
     Isles
    -0.79
     Caribbean
    -0.78
     Tune
    -0.77
     Leone
    -0.75
     Survivor
    -0.74
     Sussex
    -0.74
     Cook
    -0.70
     Maryland
    -0.70
    POSITIVE LOGITS
    oÄŁan
    1.57
     Erd
    1.00
    istry
    0.92
    \\\\\\\\
    0.91
    arb
    0.88
    uin
    0.86
    isans
    0.86
    omen
    0.85
    ocide
    0.84
    bey
    0.84
    Act Density 0.021%

    No Known Activations