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

    Neuronpedia

    INDEX
    Explanations

    terms related to movement and navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.31
    3:0.08
    4:0.14
    5:0.03
    6:0.03
    7:0.08
    8:0.05
    9:0.03
    10:0.09
    11:0.07
    Negative Logits
     Modes
    -1.65
    athi
    -1.60
     illustrated
    -1.56
    capt
    -1.53
     Nept
    -1.44
    hemat
    -1.43
     illustrates
    -1.42
     Bars
    -1.40
    arth
    -1.38
    mouse
    -1.35
    POSITIVE LOGITS
     oneself
    1.90
     cheaply
    1.47
    naissance
    1.45
     ASAP
    1.45
     hurry
    1.43
     tremend
    1.43
     lookout
    1.40
     ourselves
    1.37
     Yourself
    1.37
    bral
    1.37
    Act Density 0.037%

    No Known Activations