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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "grip" and related terms indicating a grasping or holding action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cop
    -0.15
    ncy
    -0.15
    LETE
    -0.15
    ibold
    -0.15
    nes
    -0.15
    rowse
    -0.15
    sterol
    -0.14
    lor
    -0.14
    Word
    -0.14
    vis
    -0.14
    POSITIVE LOGITS
    i
    0.27
    bose
    0.22
    ego
    0.21
    pped
    0.21
    eh
    0.20
    ps
    0.20
    eger
    0.20
    quet
    0.20
    ega
    0.20
    egen
    0.20
    Act Density 0.024%

    No Known Activations