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

    Neuronpedia

    INDEX
    Explanations

    the word "so" in various contexts and emphasize its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.80
     NgModule
    -0.80
     Majefty
    -0.75
     pleaſure
    -0.72
    ſelf
    -0.72
     AssemblyProduct
    -0.72
    iastes
    -0.70
    RetentionPolicy
    -0.70
    stdc
    -0.69
     pleaf
    -0.68
    POSITIVE LOGITS
    ยว
    0.73
    
    0.65
    dymyr
    0.62
    PointerException
    0.60
     Bock
    0.60
     שוליים
    0.59
    tenths
    0.56
     importantly
    0.55
    TintMode
    0.54
     sometimes
    0.54
    Act Density 0.140%

    No Known Activations