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

    Neuronpedia

    INDEX
    Explanations

    phrases related to holding or grasping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.11
    5:0.04
    6:0.06
    7:0.35
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    etheus
    -1.79
    renheit
    -1.63
    ciation
    -1.56
    utenant
    -1.52
    iology
    -1.52
    cius
    -1.46
    ioxide
    -1.43
    clair
    -1.40
    enz
    -1.39
     [+
    -1.38
    POSITIVE LOGITS
    stretched
    1.55
    spread
    1.52
     mercy
    1.50
     mammoth
    1.49
     cache
    1.49
     tightly
    1.47
     paws
    1.44
     hoard
    1.44
     Cache
    1.42
    Property
    1.42
    Act Density 0.001%

    No Known Activations