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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or confusion in conversations

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

    Follow-up answers starting with "A:"

    np_acts-logits-general · gemini-2.0-flash

    A: or Regarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.77
    BagConstraints
    -0.76
    XMLSchema
    -0.69
     autorytatywna
    -0.65
    àng
    -0.61
    onViewCreated
    -0.60
     requestCode
    -0.60
     nltk
    -0.60
    ufig
    -0.59
    ftagPool
    -0.57
    POSITIVE LOGITS
    OK
    0.68
     Alright
    0.64
    Alright
    0.63
     Yeah
    0.61
     Hmm
    0.60
     Wow
    0.58
    Yeah
    0.58
     Okay
    0.57
    Okay
    0.57
     Sorry
    0.55
    Act Density 0.191%

    No Known Activations