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

    Neuronpedia

    INDEX
    Explanations

    negative statements or contradictions

    oai_token-act-pair · gpt-3.5-turbo

    negation phrases or words indicating denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.74
    iery
    -0.67
    senal
    -0.66
    ngth
    -0.65
    cribed
    -0.65
    ugu
    -0.62
    obo
    -0.60
    unks
    -0.60
    owan
    -0.60
    arine
    -0.59
    POSITIVE LOGITS
    etheless
    0.82
     enough
    0.81
     necessarily
    0.77
     conclusive
    0.71
     nonetheless
    0.70
     unanimous
    0.69
     exact
    0.66
     deter
    0.65
     clin
    0.64
     sufficient
    0.63
    Act Density 0.304%

    No Known Activations