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

    Neuronpedia

    INDEX
    Explanations

    punctuations and bracketed or quoted segments of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.62
    󠁿
    -0.57
     ModelExpression
    -0.57
     snippetHide
    -0.54
    SequentialGroup
    -0.51
    клопе
    -0.51
    Personendaten
    -0.49
    awtextra
    -0.48
    urlopen
    -0.48
     فريبيس
    -0.47
    POSITIVE LOGITS
     picioare
    0.60
     enfans
    0.59
     avoient
    0.58
     stanga
    0.57
     feroit
    0.55
     étoient
    0.53
     bileklik
    0.53
     colgantes
    0.51
     cokelat
    0.51
     žel
    0.51
    Act Density 0.609%

    No Known Activations