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

    Neuronpedia

    INDEX
    Explanations

    references to specific scenarios or contexts in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.19
    zos
    -0.15
    ût
    -0.15
    ä¸ĺ
    -0.15
    VERTISE
    -0.15
    ีà¸ĭ
    -0.15
    ends
    -0.15
    riger
    -0.15
    :hidden
    -0.15
    idth
    -0.15
    POSITIVE LOGITS
     situations
    0.16
    649
    0.16
     propTypes
    0.14
    æķ¦
    0.14
     ë´IJ
    0.14
     Ritch
    0.13
     Markup
    0.13
    naires
    0.13
     greed
    0.13
     Heck
    0.13
    Act Density 0.023%

    No Known Activations