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

    Neuronpedia

    INDEX
    Explanations

    statistics or achievements related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating leadership or leading roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.74
    arthy
    -0.70
    emis
    -0.69
     exile
    -0.67
    agn
    -0.66
    iannopoulos
    -0.65
     licences
    -0.62
    enegger
    -0.61
     concess
    -0.61
    orrow
    -0.60
    POSITIVE LOGITS
     scorer
    0.88
    owed
    0.70
    leaders
    0.69
    CU
    0.69
     Blazers
    0.69
     Trophy
    0.68
    combe
    0.67
    ership
    0.66
    leading
    0.65
    better
    0.65
    Act Density 0.040%

    No Known Activations