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

    Neuronpedia

    INDEX
    Explanations

    phrases that express occurrences of "that" followed by various actions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mun
    -0.15
    entions
    -0.15
    545
    -0.15
    amin
    -0.15
    pte
    -0.14
    anda
    -0.14
    436
    -0.14
    hta
    -0.14
    à¹Ģà¸Ĺ
    -0.14
    337
    -0.14
    POSITIVE LOGITS
    еÑĢо
    0.18
     nÃło
    0.16
    ymax
    0.15
    živ
    0.15
    yro
    0.14
    ERGE
    0.14
    berra
    0.14
     NSStringFromClass
    0.13
    SCRI
    0.13
    ModelError
    0.13
    Act Density 0.016%

    No Known Activations