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

    Neuronpedia

    INDEX
    Explanations

    references to celebrities and their appearances in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اص
    -0.09
    zyst
    -0.08
    âĦĸâĦĸ
    -0.08
    lace
    -0.08
    RITE
    -0.08
    ãģ¡ãģ¯
    -0.08
    .IContainer
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
    roperty
    -0.07
    ìľłë¨¸
    -0.07
    POSITIVE LOGITS
     (
    0.07
     imaginary
    0.06
     "
    0.06
     fake
    0.06
    iga
    0.06
     segments
    0.05
    Âł
    0.05
     Introduced
    0.05
     Direct
    0.05
     introduced
    0.05
    Act Density 0.009%

    No Known Activations