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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and comparisons between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?,?,?,?,
    -0.25
     Eleven
    -0.15
    $MESS
    -0.15
    OffsetTable
    -0.14
    Seven
    -0.13
    جات
    -0.13
    hiba
    -0.13
    é§ħå¾ĴæŃ©
    -0.13
    Nine
    -0.13
    Eight
    -0.12
    POSITIVE LOGITS
     two
    1.27
    two
    1.05
     TWO
    0.91
     Two
    0.91
    两个
    0.88
    Two
    0.85
    _two
    0.85
    -two
    0.85
     deux
    0.84
     zwei
    0.83
    Act Density 0.745%

    No Known Activations