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

    Neuronpedia

    INDEX
    Explanations

    instances of the character “)”, likely indicating emotional expressions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.22
    2:0.07
    3:0.08
    4:0.02
    5:0.13
    6:0.01
    7:0.08
    8:0.03
    9:0.08
    10:0.06
    11:0.10
    Negative Logits
    poke
    -1.77
    kernel
    -1.74
    goo
    -1.67
    dogs
    -1.60
    trip
    -1.60
    cakes
    -1.58
    ventures
    -1.56
    instance
    -1.55
    match
    -1.55
    air
    -1.54
    POSITIVE LOGITS
    endon
    1.53
    Cooldown
    1.51
     Directorate
    1.44
     shrug
    1.40
    ]);
    1.40
     stressed
    1.39
     Noon
    1.38
     goodbye
    1.38
     deval
    1.37
     UNCLASSIFIED
    1.35
    Act Density 0.001%

    No Known Activations