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

    Neuronpedia

    INDEX
    Explanations

    specific verb forms and certain prefixes or roots that indicate actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weld
    -0.20
    stalk
    -0.20
     remodel
    -0.20
    unfold
    -0.19
    _paint
    -0.18
    odcast
    -0.17
    uvre
    -0.17
    _walk
    -0.17
    imizer
    -0.17
    PEND
    -0.17
    POSITIVE LOGITS
    lapping
    0.20
    ricing
    0.20
    landing
    0.19
    loating
    0.19
    inking
    0.18
    reeting
    0.18
    oothing
    0.18
    rending
    0.18
    amping
    0.18
    umbing
    0.18
    Act Density 0.179%

    No Known Activations