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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that emphasize qualifications or characteristics of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inarily
    -0.75
    rawdownloadcloneembedreportprint
    -0.68
     srfAttach
    -0.68
    iple
    -0.66
    anguage
    -0.65
     richness
    -0.64
    iture
    -0.64
    agascar
    -0.63
    ragon
    -0.63
    ãĤª
    -0.63
    POSITIVE LOGITS
    ournal
    0.82
    Gil
    0.81
     Higgins
    0.75
    Adams
    0.73
     Marriott
    0.72
     Gaw
    0.71
     Ballard
    0.71
     Rowling
    0.70
    TAG
    0.69
     Weld
    0.69
    Act Density 0.038%

    No Known Activations