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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherland
    -0.17
    LETE
    -0.17
    egal
    -0.16
    tere
    -0.15
    orraine
    -0.15
     jo
    -0.14
    illi
    -0.14
    847
    -0.14
    846
    -0.14
    dux
    -0.14
    POSITIVE LOGITS
     Guth
    0.17
    porno
    0.16
    adle
    0.16
    affer
    0.15
    êµ°
    0.15
    à¹Ģà¸Ľà¸Ńร
    0.15
    YSIS
    0.15
     cart
    0.14
    bote
    0.14
    avian
    0.14
    Act Density 0.000%

    No Known Activations