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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text segments or document structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPATH
    -0.60
    ))),
    -0.56
    )^{-
    -0.56
     recensement
    -0.56
    Hentet
    -0.56
    )))))
    -0.56
    GeoNames
    -0.55
     للاسماء
    -0.54
     Moraes
    -0.54
     שוליים
    -0.54
    POSITIVE LOGITS
     betweenstory
    0.82
    TacToe
    0.80
     esternos
    0.78
    axa
    0.72
    phazard
    0.70
    axx
    0.67
    requency
    0.67
    avax
    0.65
    xes
    0.65
    cifix
    0.65
    Act Density 0.042%

    No Known Activations