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

    Neuronpedia

    INDEX
    Explanations

    calls to action or public statements prompting for social change

    oai_token-act-pair · gpt-3.5-turbo

    calls to action directed at addressing social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aple
    -0.78
    anke
    -0.66
    WN
    -0.65
     mids
    -0.61
     sake
    -0.60
    etheless
    -0.60
     belie
    -0.60
     satisfies
    -0.60
    igree
    -0.59
    tions
    -0.59
    POSITIVE LOGITS
     bluff
    0.79
    EStream
    0.75
    SpaceEngineers
    0.68
    Choice
    0.68
    tera
    0.66
    dan
    0.65
    unal
    0.65
    arth
    0.65
     kettle
    0.64
    Fax
    0.64
    Act Density 0.258%

    No Known Activations