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

    Neuronpedia

    INDEX
    Explanations

    expressions of tiredness or frustration with repetitive or unoriginal concepts

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

    Followed by punctuation or a function word

    np_acts-logits-general · gemini-2.0-flash

    repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     án
    -0.43
    octanol
    -0.43
    LabelTagHelper
    -0.42
    igneurs
    -0.41
    BufferException
    -0.39
    Scaler
    -0.39
    нак
    -0.39
    beiro
    -0.39
     richtige
    -0.39
    localScale
    -0.38
    POSITIVE LOGITS
     repetition
    1.66
     repetitive
    1.64
     repeats
    1.60
     repeating
    1.59
     repeated
    1.58
     repeti
    1.54
    repeated
    1.53
     repeat
    1.52
     Repetition
    1.51
     Repeated
    1.51
    Act Density 0.279%

    No Known Activations