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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or incredulity

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

    astonishment and disbelief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.37
     $?
    -0.36
    Koordinaten
    -0.35
    SuspendLayout
    -0.35
    клопе
    -0.33
     primarily
    -0.33
    erdings
    -0.33
    RuleContext
    -0.32
    HasOne
    -0.32
     tartalomajánló
    -0.32
    POSITIVE LOGITS
    incredible
    0.89
    Incredible
    0.84
     unbelievable
    0.84
    amazing
    0.81
    shocked
    0.77
     incredi
    0.74
     incredible
    0.73
    Amazing
    0.72
     Incredible
    0.71
     incroy
    0.71
    Act Density 0.004%

    No Known Activations