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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and numbers, indicating a focus on statistical or categorical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.17
    int
    -0.15
    ouve
    -0.14
    quette
    -0.14
    throp
    -0.14
     hur
    -0.14
    thon
    -0.14
    FA
    -0.14
    ule
    -0.14
    porte
    -0.13
    POSITIVE LOGITS
    aland
    0.14
    uforia
    0.14
    abez
    0.14
    rosse
    0.13
    sis
    0.13
    Aceptar
    0.13
    ERNEL
    0.13
    opard
    0.13
    alore
    0.13
    çį
    0.13
    Act Density 0.016%

    No Known Activations