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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical alignments or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Above
    -0.61
    Above
    -0.57
    (!__
    -0.56
    NameInMap
    -0.56
     discorso
    -0.52
     Roskov
    -0.52
     above
    -0.51
     discussione
    -0.49
     tetto
    -0.49
     Arki
    -0.49
    POSITIVE LOGITS
    awtextra
    0.71
    IntoConstraints
    0.58
     ujednoznacz
    0.53
    tanleria
    0.52
    GINIA
    0.52
    ArgsConstructor
    0.51
    Iden
    0.50
    AddRef
    0.50
     PicClick
    0.49
    HomeAsUpEnabled
    0.49
    Act Density 0.047%

    No Known Activations