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

    Neuronpedia

    INDEX
    Explanations

    references to dialogues or interviews involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.11
    4:0.14
    5:0.02
    6:0.03
    7:0.13
    8:0.02
    9:0.03
    10:0.12
    11:0.24
    Negative Logits
    �
    -1.47
    reply
    -1.45
    Activity
    -1.45
     greeting
    -1.40
     entertained
    -1.40
    Talking
    -1.37
    realDonaldTrump
    -1.34
    reetings
    -1.34
     convers
    -1.32
    OTE
    -1.31
    POSITIVE LOGITS
     rarity
    1.55
     Alb
    1.43
    nesses
    1.35
     PSP
    1.32
    phis
    1.32
    eria
    1.30
     penalties
    1.28
     Lump
    1.27
     Fract
    1.26
     Ratio
    1.23
    Act Density 0.066%

    No Known Activations