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

    Neuronpedia

    INDEX
    Explanations

    questions and statements of disbelief or incredulity

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

    Expressing disbelief or disagreement

    np_acts-logits-general · gemini-2.0-flash

    exasperated "i mean"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.73
     purtroppo
    -0.60
    ')):
    -0.55
    ailleurs
    -0.55
     сожалению
    -0.53
    NUMX
    -0.53
     getItemCount
    -0.52
     ""));
    -0.52
     malheureusement
    -0.52
     '+':
    -0.50
    POSITIVE LOGITS
     seriously
    1.24
    Seriously
    1.21
     Seriously
    1.19
    seriously
    1.15
     wtf
    1.09
     Wtf
    1.08
     WTF
    1.08
     sérieux
    0.93
     sério
    0.91
    wtf
    0.90
    Act Density 0.195%

    No Known Activations