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

    Neuronpedia

    INDEX
    Explanations

    numerical representations referring to document formats or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.14
    2:0.08
    3:0.03
    4:0.04
    5:0.12
    6:0.07
    7:0.02
    8:0.26
    9:0.05
    10:0.03
    11:0.05
    Negative Logits
     understatement
    -2.06
     suffice
    -1.62
     sidx
    -1.57
     complied
    -1.56
     curve
    -1.52
     namely
    -1.50
     denotes
    -1.47
     dotted
    -1.46
     signifies
    -1.46
     ensemble
    -1.46
    POSITIVE LOGITS
    WAR
    2.04
    Fa
    1.91
    aroo
    1.90
    Person
    1.86
    BTC
    1.83
    Y
    1.81
    Pic
    1.79
    Merit
    1.78
    Da
    1.78
    TAG
    1.76
    Act Density 0.001%

    No Known Activations