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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence and quantity of specific items or categories within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.70
     anhyd
    -0.70
     onAnimation
    -0.67
    AndEndTag
    -0.66
     EconPapers
    -0.65
     Cæsar
    -0.64
     Partagez
    -0.63
     مرئيه
    -0.63
     Tatar
    -0.63
    InputBorder
    -0.63
    POSITIVE LOGITS
     antaranya
    0.61
    IsContent
    0.54
    うち
    0.53
     diantaranya
    0.52
    jspb
    0.51
    其中
    0.47
     cor
    0.45
     bek
    0.44
     die
    0.44
    antaranya
    0.44
    Act Density 0.324%

    No Known Activations