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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial obligations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.06
    4:0.17
    5:0.04
    6:0.05
    7:0.30
    8:0.03
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
    pedia
    -1.66
    ipedia
    -1.62
    zai
    -1.61
    Witness
    -1.53
    unin
    -1.47
    SPONSORED
    -1.45
     Surveillance
    -1.35
    kie
    -1.32
     Celebration
    -1.31
    Race
    -1.31
    POSITIVE LOGITS
     redundant
    1.50
    loading
    1.41
    Condition
    1.40
     serv
    1.39
     surplus
    1.36
     Provided
    1.35
     constant
    1.30
     Negative
    1.28
     €
    1.27
    Fixed
    1.27
    Act Density 0.000%

    No Known Activations