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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal growth and self-improvement

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions related to change and personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.81
    uly
    -0.79
     reception
    -0.78
    thal
    -0.73
    anni
    -0.73
     intended
    -0.73
    abouts
    -0.72
    onga
    -0.71
    umerous
    -0.71
    uese
    -0.70
    POSITIVE LOGITS
     Sometimes
    1.15
     Especially
    1.13
     Whether
    1.13
     And
    1.12
     Whatever
    1.11
     Nothing
    1.08
     Unless
    1.07
     Without
    1.07
     Knowing
    1.05
     Otherwise
    1.05
    Act Density 0.623%

    No Known Activations