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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty about future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or the potential for future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     labou
    -0.60
     ousted
    -0.59
     deficit
    -0.58
     objectionable
    -0.58
     radicals
    -0.57
     neut
    -0.56
     defective
    -0.56
     protesters
    -0.55
     transferred
    -0.55
     organised
    -0.55
    POSITIVE LOGITS
     Allaah
    0.83
    lege
    0.74
    eye
    0.72
    rue
    0.72
     speculate
    0.71
    unknown
    0.71
     discretion
    0.69
    miah
    0.69
    ħĭ
    0.68
    moon
    0.68
    Act Density 0.456%

    No Known Activations