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

    Neuronpedia

    INDEX
    Explanations

    financial figures and numerical data related to costs and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.26
    1:0.02
    2:0.02
    3:0.07
    4:0.05
    5:0.11
    6:0.07
    7:0.02
    8:0.11
    9:0.11
    10:0.02
    11:0.08
    Negative Logits
     neutrality
    -1.83
    hooting
    -1.66
    ewater
    -1.66
     audiences
    -1.65
    ability
    -1.64
    alking
    -1.62
    cipled
    -1.61
    livious
    -1.51
    htaking
    -1.46
    watching
    -1.46
    POSITIVE LOGITS
    -$
    2.15
    £
    1.92
     USD
    1.89
    ]),
    1.80
     GMT
    1.77
    /$
    1.74
     purse
    1.71
     yen
    1.68
    $.
    1.60
     (£
    1.60
    Act Density 0.003%

    No Known Activations