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

    Neuronpedia

    INDEX
    Explanations

    words and punctuation related to quotations and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laden
    -0.16
    aminer
    -0.16
     Complete
    -0.15
    avanaugh
    -0.15
     Mic
    -0.15
    ahi
    -0.14
    ouro
    -0.14
    usta
    -0.14
     Winner
    -0.14
    .ba
    -0.14
    POSITIVE LOGITS
    .matcher
    0.15
    =ax
    0.14
     Matcher
    0.14
    antee
    0.14
    -safe
    0.14
    imu
    0.14
    esium
    0.14
    allax
    0.13
    INARY
    0.13
    eyJ
    0.13
    Act Density 0.226%

    No Known Activations