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

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjud
    -0.84
     favour
    -0.84
     tyre
    -0.69
     referee
    -0.67
     grammar
    -0.65
     furn
    -0.64
     transl
    -0.64
     referees
    -0.64
     organisers
    -0.64
     narr
    -0.64
    POSITIVE LOGITS
    We
    1.19
    Our
    1.11
    Clearly
    1.11
    Today
    1.07
    They
    1.07
    There
    1.06
    It
    1.06
    Trust
    1.05
    Obviously
    1.04
    Republicans
    1.04
    Act Density 0.131%

    No Known Activations