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

    Neuronpedia

    INDEX
    Explanations

    academic titles and positions in research settings

    oai_token-act-pair · gpt-3.5-turbo

    academic titles and affiliations related to research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decency
    -0.76
     softer
    -0.73
     craz
    -0.72
     inconven
    -0.68
    AAF
    -0.68
     brav
    -0.68
     repe
    -0.67
     corrid
    -0.67
     disapp
    -0.66
     frust
    -0.66
    POSITIVE LOGITS
    inguished
    0.92
    doctoral
    0.91
    uates
    0.89
     Faculty
    0.86
     IEEE
    0.84
    lished
    0.83
     doctoral
    0.82
    study
    0.78
    lies
    0.78
     dissertation
    0.77
    Act Density 0.147%

    No Known Activations