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

    Neuronpedia

    INDEX
    Explanations

    ellipses and other forms of textual omissions or pauses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hesitations and filler words

    np_acts-logits-general · gemini-2.0-flash

    verbal pauses and filler words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -0.81
     للمعارف
    -0.64
     مرئيه
    -0.64
    出版年
    -0.61
    ="@+
    -0.61
    ioutil
    -0.58
    깥
    -0.58
    PreInfinity
    -0.57
     depic
    -0.57
     BrowserModule
    -0.56
    POSITIVE LOGITS
    …
    0.77
     erm
    0.77
     umm
    0.76
     sorta
    0.68
    “…
    0.66
    hem
    0.66
    ”…
    0.65
    uh
    0.64
    …”
    0.64
     kinda
    0.64
    Act Density 0.130%

    No Known Activations