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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.84
    HomeAsUpEnabled
    -0.74
    SharedCtor
    -0.70
     ISNI
    -0.67
    UnusedPrivate
    -0.66
    сылкі
    -0.66
    willReturn
    -0.64
     asciug
    -0.64
    发表于
    -0.63
    Anhalt
    -0.62
    POSITIVE LOGITS
     how
    0.52
    :
    0.50
    Berikut
    0.50
    pyr
    0.49
    таратура
    0.48
    -¿
    0.48
    Fatalf
    0.47
    Rollback
    0.47
     valign
    0.47
    เภ
    0.46
    Act Density 0.106%

    No Known Activations