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

    Neuronpedia

    INDEX
    Explanations

    instances of recognition or acknowledgment in relation to entities and sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.06
    4:0.10
    5:0.03
    6:0.04
    7:0.42
    8:0.03
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    ounty
    -1.83
     moratorium
    -1.67
    inion
    -1.56
     reluct
    -1.54
    enture
    -1.52
    exclusive
    -1.52
     obser
    -1.51
     unrestricted
    -1.50
     recons
    -1.50
    aceutical
    -1.49
    POSITIVE LOGITS
     Photographer
    1.59
     visually
    1.52
     fingerprints
    1.51
     Fighters
    1.51
     Symbol
    1.47
     Bastard
    1.44
     Geh
    1.41
    SAY
    1.40
    EMOTE
    1.39
     Thief
    1.39
    Act Density 0.011%

    No Known Activations