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

    Neuronpedia

    INDEX
    Explanations

    political statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    the specific character "âĢ¦"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favour
    -0.87
    \":
    -0.73
     sails
    -0.69
     ages
    -0.68
     intern
    -0.68
    iking
    -0.65
     untouched
    -0.65
     becoming
    -0.65
     pharmacy
    -0.65
     informing
    -0.64
    POSITIVE LOGITS
    However
    0.93
    ONSORED
    0.89
    Also
    0.89
    Therefore
    0.83
    They
    0.80
    cknowled
    0.80
    Different
    0.80
    There
    0.79
    See
    0.79
    Its
    0.79
    Act Density 0.104%

    No Known Activations