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

    Neuronpedia

    INDEX
    Explanations

    technical terminology or jargon related to user manuals and guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =================================================================================
    -0.15
    ¦
    -0.15
    Ï
    -0.14
    adle
    -0.14
    asta
    -0.14
    orraine
    -0.14
    lbs
    -0.14
    inton
    -0.13
    ispens
    -0.13
     hon
    -0.13
    POSITIVE LOGITS
    ÑĪка
    0.16
    svp
    0.15
    prenom
    0.14
    -animate
    0.14
     Ellison
    0.14
    yne
    0.14
    MaxY
    0.14
     ãĢĥ
    0.14
    .Generated
    0.13
    aise
    0.13
    Act Density 0.029%

    No Known Activations