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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts being made between different things

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating "other than."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Accessory
    -0.72
    lied
    -0.69
    ugal
    -0.69
    ished
    -0.65
    urther
    -0.65
    ula
    -0.65
    otaur
    -0.63
    ierce
    -0.63
    mob
    -0.63
    overed
    -0.62
    POSITIVE LOGITS
    stellar
    0.70
     NULL
    0.69
     ours
    0.65
    hetics
    0.65
    aqu
    0.63
     namely
    0.63
     those
    0.63
    ournal
    0.60
    ascript
    0.60
     hers
    0.57
    Act Density 0.024%

    No Known Activations