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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protrusion or extension of body parts and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سÙģ
    -0.15
    gili
    -0.15
    avez
    -0.15
    opes
    -0.15
    urd
    -0.15
     Sokol
    -0.14
    utter
    -0.14
     patter
    -0.14
    etine
    -0.13
    .Experimental
    -0.13
    POSITIVE LOGITS
     protr
    0.33
     bul
    0.22
     projecting
    0.22
     extended
    0.21
     sticking
    0.20
    /extensions
    0.20
     extend
    0.20
     extensions
    0.19
     extending
    0.19
    Projection
    0.19
    Act Density 0.180%

    No Known Activations