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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people and their occupations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "work" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¼
    -0.69
    ibia
    -0.64
    urdy
    -0.63
    emonic
    -0.62
    theless
    -0.60
    ythm
    -0.60
    cemic
    -0.59
    xual
    -0.59
     gratification
    -0.59
    ovi
    -0.59
    POSITIVE LOGITS
     tirelessly
    0.99
     undercover
    0.97
     alongside
    0.92
     extensively
    0.87
     closely
    0.83
     abroad
    0.82
     internship
    0.80
     diligently
    0.77
     overseas
    0.77
    hops
    0.77
    Act Density 0.079%

    No Known Activations