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

    Neuronpedia

    INDEX
    Explanations

    country names and organizations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and conjunction-like elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.70
    icka
    -0.65
    usercontent
    -0.65
    ruary
    -0.63
    atform
    -0.60
     Revis
    -0.57
     cruiser
    -0.57
     rewritten
    -0.57
    forth
    -0.57
     err
    -0.57
    POSITIVE LOGITS
    ãĥĨ
    0.80
    igham
    0.74
    bors
    0.70
    emies
    0.69
     buds
    0.63
    ãĥł
    0.62
    achus
    0.61
    song
    0.61
    arth
    0.61
    eping
    0.61
    Act Density 0.411%

    No Known Activations