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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģ«
    -0.75
     tune
    -0.73
     stolen
    -0.66
    ween
    -0.62
     CLS
    -0.62
     butterflies
    -0.62
    plete
    -0.61
     concurrent
    -0.61
     surfing
    -0.60
     trapping
    -0.59
    POSITIVE LOGITS
    utenberg
    0.81
     presided
    0.77
    oyer
    0.76
     chaired
    0.73
    ynski
    0.73
     apologised
    0.72
    iman
    0.72
     thanked
    0.71
    urai
    0.71
     oversaw
    0.71
    Act Density 0.218%

    No Known Activations