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

    Neuronpedia

    INDEX
    Explanations

    references to large, disruptive parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remar
    -0.18
     lunch
    -0.18
     lunches
    -0.16
     Lunch
    -0.16
     tea
    -0.16
    pta
    -0.16
    ffee
    -0.15
    imers
    -0.15
     coffee
    -0.14
    andin
    -0.14
    POSITIVE LOGITS
     party
    0.39
     PARTY
    0.30
    party
    0.30
    -party
    0.29
     Party
    0.29
    Party
    0.28
    _party
    0.28
     parties
    0.28
    .party
    0.22
     bac
    0.22
    Act Density 0.117%

    No Known Activations