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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and analysis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escaping
    -0.15
    [âĢ¦
    -0.14
    âĢ¦and
    -0.14
    âĢ¦but
    -0.14
    âĢ¦it
    -0.14
    첨ë¶Ģ
    -0.13
     Westbrook
    -0.13
     Scalars
    -0.13
    âĢ¦I
    -0.13
    âĢ¦.
    -0.12
    POSITIVE LOGITS
    arat
    0.13
    affle
    0.13
    Æ°á»Ľ
    0.13
    òi
    0.13
    .Highlight
    0.13
    обов
    0.13
    opak
    0.13
    .Params
    0.13
    ç´¹
    0.13
    quot
    0.13
    Act Density 1.758%

    No Known Activations