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

    Neuronpedia

    INDEX
    Explanations

    references to titles or honorifics, particularly "Sir."

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

    Appears next to titles or honorifics

    np_acts-logits-general · gemini-2.0-flash

    Sir, PROS, Ann, different, rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    off
    -0.60
     off
    -0.56
    phrine
    -0.56
    Off
    -0.53
     Off
    -0.51
    sbereich
    -0.49
     stream
    -0.48
    MigrationBuilder
    -0.45
    ToUpdate
    -0.45
    setVerticalGroup
    -0.45
    POSITIVE LOGITS
     GenerationType
    0.75
     nakalista
    0.70
    numerusform
    0.65
    AutoScale
    0.64
    aspectj
    0.64
    EDEFAULT
    0.64
    RequiresApi
    0.64
     CreateTagHelper
    0.62
    HasForeignKey
    0.62
     ComVisible
    0.61
    Act Density 0.200%

    No Known Activations