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

    Neuronpedia

    INDEX
    Explanations

    the introductory phrase "So" used to transition or summarize thoughts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Damit
    -0.82
     Damit
    -0.80
     Spisak
    -0.78
     Wadsworth
    -0.78
     ensu
    -0.73
     ChromeDriver
    -0.72
     Daher
    -0.71
     thus
    -0.68
    TypedDataSet
    -0.66
    hésite
    -0.66
    POSITIVE LOGITS
    addContainerGap
    0.63
     maxn
    0.62
    ModelState
    0.57
     برابوك
    0.56
     cat
    0.55
    KEYCODE
    0.55
    toHaveBeenCalled
    0.54
    ={<
    0.54
     hals
    0.54
    csname
    0.53
    Act Density 0.015%

    No Known Activations