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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "so" and its variations, indicating a focus on expressions of consequence or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.89
     дописавши
    -0.88
     nakalista
    -0.86
    DIPSETTING
    -0.80
     itſelf
    -0.77
    uminense
    -0.76
    "]);
    -0.75
     препратки
    -0.75
     myſelf
    -0.73
    adpleegd
    -0.72
    POSITIVE LOGITS
    So
    2.44
     So
    2.30
    SO
    2.26
     SO
    2.06
    so
    1.81
     Soc
    1.03
    ソ
    1.00
     Со
    0.95
     Soak
    0.94
     Sou
    0.93
    Act Density 0.103%

    No Known Activations