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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tax contributions and fundraising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.01
    2:0.04
    3:0.22
    4:0.08
    5:0.11
    6:0.04
    7:0.06
    8:0.04
    9:0.01
    10:0.23
    11:0.04
    Negative Logits
     coordin
    -2.12
     intric
    -1.99
    liest
    -1.98
     coordinated
    -1.95
     coordinate
    -1.93
     jails
    -1.93
     proportions
    -1.91
     coordinating
    -1.90
     lobb
    -1.89
     disproportion
    -1.82
    POSITIVE LOGITS
    Continue
    2.24
     Lens
    2.08
    Hour
    2.06
    Return
    1.95
     Hour
    1.86
    Later
    1.85
    SPONSORED
    1.81
     Later
    1.79
     Return
    1.77
    hour
    1.77
    Act Density 0.001%

    No Known Activations