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

    Neuronpedia

    INDEX
    Explanations

    physical actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.07
    4:0.14
    5:0.03
    6:0.03
    7:0.34
    8:0.04
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
    sonian
    -2.38
    priority
    -1.76
    eworks
    -1.71
    uilding
    -1.68
    cellent
    -1.61
    CLUS
    -1.61
    rative
    -1.60
    exclusive
    -1.60
    endars
    -1.59
    uments
    -1.57
    POSITIVE LOGITS
     recoil
    1.74
     shy
    1.59
     overhe
    1.55
     overe
    1.54
     sudden
    1.47
     whiff
    1.45
     losing
    1.40
     Butt
    1.39
     footsteps
    1.38
     overly
    1.37
    Act Density 0.001%

    No Known Activations