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

    Neuronpedia

    INDEX
    Explanations

    statements made by people

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berus
    -0.71
    pend
    -0.66
    azines
    -0.61
    anges
    -0.60
    anuts
    -0.58
    cession
    -0.58
    ective
    -0.58
     conflic
    -0.58
    Fit
    -0.57
    phia
    -0.56
    POSITIVE LOGITS
     sarcast
    1.17
     rhet
    1.07
     bluntly
    1.04
     onstage
    1.03
     emphatically
    0.97
     during
    0.96
     afterward
    0.88
     passionately
    0.84
     forcefully
    0.83
     aloud
    0.83
    Act Density 0.132%

    No Known Activations