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

    Neuronpedia

    INDEX
    Explanations

    the presence of the token indicating the beginning of a new section or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    8
    -0.55
    4
    -0.53
    9
    -0.52
    6
    -0.50
     below
    -0.49
    3
    -0.48
    1
    -0.48
    7
    -0.48
    5
    -0.47
    de
    -0.47
    POSITIVE LOGITS
    Portale
    1.18
     Roskov
    1.07
     للاسماء
    0.96
     EconPapers
    0.85
    Portail
    0.83
     незавершена
    0.82
    исленность
    0.78
    WriteTagHelper
    0.78
    Geplaatst
    0.78
    بوابة
    0.76
    Act Density 0.026%

    No Known Activations