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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and pauses in dialogue or narrative structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gee
    -0.15
    便
    -0.15
     cÃłng
    -0.15
    ult
    -0.14
    .gg
    -0.14
    uth
    -0.14
    ãĥªãĤ«
    -0.13
    åĭ¤
    -0.13
    ognito
    -0.13
     getSystemService
    -0.13
    POSITIVE LOGITS
     sort
    0.38
     sorts
    0.35
     Sort
    0.33
     well
    0.33
    sort
    0.32
    Sort
    0.30
     literally
    0.27
    well
    0.27
     Liter
    0.27
     actually
    0.25
    Act Density 0.205%

    No Known Activations