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

    Neuronpedia

    INDEX
    Explanations

    questions and statements related to uncertainty or criticism

    oai_token-act-pair · gpt-3.5-turbo

    negative questions and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rehend
    -0.57
    ablishment
    -0.57
     Kun
    -0.57
    osate
    -0.56
    iatrics
    -0.56
     Sapp
    -0.55
    VERTISEMENT
    -0.54
    ileged
    -0.54
     Success
    -0.53
     Tropical
    -0.53
    POSITIVE LOGITS
    pecially
    0.90
    cause
    0.89
     preferring
    0.82
    etheless
    0.75
    _>
    0.71
    especially
    0.69
     suggesting
    0.68
    but
    0.66
    akin
    0.65
     notwithstanding
    0.65
    Act Density 0.401%

    No Known Activations