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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and their accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.50
    2:0.03
    3:0.05
    4:0.03
    5:0.07
    6:0.04
    7:0.03
    8:0.03
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    acs
    -2.87
     someday
    -2.54
    アル
    -2.53
     Sloven
    -2.46
    option
    -2.42
     achievable
    -2.35
     Cooke
    -2.34
    isson
    -2.33
     Courage
    -2.27
     Sao
    -2.26
    POSITIVE LOGITS
     17
    4.45
    17
    4.39
    18
    3.44
     18
    3.44
    eteenth
    3.38
     eighteenth
    3.27
     1700
    3.20
     16
    3.13
    eteen
    3.13
    uko
    3.12
    Act Density 0.008%

    No Known Activations