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

    Neuronpedia

    INDEX
    Explanations

    monetary values or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.06
    4:0.08
    5:0.06
    6:0.09
    7:0.09
    8:0.07
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
     adjourn
    -1.84
     Robb
    -1.84
     Briggs
    -1.78
     Conan
    -1.69
     ensuring
    -1.67
     Starr
    -1.63
     repr
    -1.62
     Bennett
    -1.61
     Razer
    -1.59
     overtime
    -1.59
    POSITIVE LOGITS
    cius
    2.13
    20439
    2.12
    oplan
    2.09
    htaking
    2.08
    thood
    2.00
    rex
    1.99
    idences
    1.98
    rencies
    1.90
    levels
    1.86
    retty
    1.80
    Act Density 0.000%

    No Known Activations