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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    present participles and gerunds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.69
    ihar
    -0.64
     drinking
    -0.62
    Ô
    -0.60
     streaming
    -0.59
     calming
    -0.58
     conclud
    -0.58
     gathering
    -0.58
     spelling
    -0.58
    ¿½
    -0.57
    POSITIVE LOGITS
    tons
    1.43
    ham
    1.30
    ton
    1.20
    HAM
    1.12
    haus
    1.06
    redients
    1.04
    uez
    1.01
    hani
    0.94
    lass
    0.93
    bird
    0.92
    Act Density 0.078%

    No Known Activations