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

    Neuronpedia

    INDEX
    Explanations

    formal salutations and openings in correspondence

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

    opening salutations with "Dear"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stylers
    -0.38
     NSCoder
    -0.35
    DIPSETTING
    -0.35
    RuleContext
    -0.35
    adaptiveStyles
    -0.35
    onsored
    -0.34
     løpet
    -0.34
    JNIEnv
    -0.34
    wahati
    -0.34
    arakhand
    -0.33
    POSITIVE LOGITS
    Dear
    0.58
     letter
    0.56
     dear
    0.54
     Dear
    0.54
     lettera
    0.51
    DEAR
    0.51
     Wolfgang
    0.50
    dear
    0.50
    WithIOException
    0.49
     deſſen
    0.49
    Act Density 0.011%

    No Known Activations