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

    Neuronpedia

    INDEX
    Explanations

    the beginning of paragraphs or sections within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.71
     (
    -0.53
     in
    -0.48
    for
    -0.47
     [
    -0.46
     form
    -0.46
     en
    -0.46
    ,
    -0.45
    assa
    -0.44
     non
    -0.44
    POSITIVE LOGITS
    tvguidetime
    1.17
     tartalomajánló
    1.09
    expandindo
    1.07
     surla
    1.06
     Wicidata
    1.01
     виправивши
    0.99
    存于互联网档案馆
    0.98
     للمعارف
    0.98
    enderror
    0.96
    SequentialGroup
    0.96
    Act Density 0.008%

    No Known Activations