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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing probability or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.29
    2:0.03
    3:0.03
    4:0.03
    5:0.14
    6:0.05
    7:0.02
    8:0.07
    9:0.06
    10:0.04
    11:0.05
    Negative Logits
    к
    -1.79
    �
    -1.79
    USER
    -1.73
    ザ
    -1.71
    Company
    -1.70
    AC
    -1.69
    Beh
    -1.65
    闘
    -1.64
     McM
    -1.62
     Acer
    -1.59
    POSITIVE LOGITS
     rush
    2.05
     sensitive
    1.82
     tough
    1.80
     fruitful
    1.80
     impossible
    1.78
     tense
    1.76
    aha
    1.76
     recomm
    1.75
     difficult
    1.75
     dare
    1.74
    Act Density 0.013%

    No Known Activations