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

    Neuronpedia

    INDEX
    Explanations

    mentions of current activities or states

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize identity and self-description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FU
    -0.72
     Packs
    -0.71
    ums
    -0.67
    EMS
    -0.67
     ///
    -0.65
    ifice
    -0.64
     Combine
    -0.63
    Float
    -0.63
     conflic
    -0.59
    Matrix
    -0.59
    POSITIVE LOGITS
     thankful
    0.90
     fortunate
    0.86
     lucky
    0.79
     grateful
    0.77
     confident
    0.77
     glad
    0.74
    yss
    0.72
     privileged
    0.72
     proud
    0.71
    ozyg
    0.68
    Act Density 0.340%

    No Known Activations