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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.09
    2:0.08
    3:0.09
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
     defeats
    -2.31
     bombings
    -2.19
    wrapper
    -2.17
    OTA
    -2.13
     Vaj
    -2.12
     airstrikes
    -2.07
     certification
    -2.02
     Typhoon
    -1.96
     UD
    -1.95
    ::::::::
    -1.94
    POSITIVE LOGITS
    mates
    2.55
    ettes
    2.39
    sonian
    2.39
    inge
    2.32
    enes
    2.31
    iles
    2.21
    ources
    2.19
     spons
    2.17
    archive
    2.13
    src
    2.06
    Act Density 0.000%

    No Known Activations