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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to governance and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     f
    -0.57
     sp
    -0.56
    ,
    -0.49
     for
    -0.48
     still
    -0.47
     and
    -0.47
     in
    -0.46
     BoxFit
    -0.46
     man
    -0.44
     
    -0.44
    POSITIVE LOGITS
     Majefty
    1.17
    GEBURTSDATUM
    1.08
     Мексичка
    1.05
     ſche
    1.05
     Houſe
    1.02
     ſeveral
    1.01
     Diſ
    0.98
    tagHelperRunner
    0.97
    LookAnd
    0.96
    ſelf
    0.96
    Act Density 2.711%

    No Known Activations