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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases and transitional cues in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -1.03
    Rujuakan
    -1.00
    __':
    -0.99
     MainAxisSize
    -0.99
    MessageState
    -0.99
     Audiodateien
    -0.99
    ंदीखरीदारी
    -0.98
     EconPapers
    -0.98
    adaptiveStyles
    -0.96
    ("")]
    -0.96
    POSITIVE LOGITS
     
    0.80
    ,
    0.79
    ↵
    0.76
    <strong>
    0.70
     in
    0.69
    .
    0.66
    </em>
    0.65
    <eos>
    0.63
     a
    0.63
     as
    0.62
    Act Density 0.593%

    No Known Activations