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

    Neuronpedia

    INDEX
    Explanations

    derivative or morphological forms of adjectives related to appearance or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adjectives ending in -ed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eyes
    -0.75
     lungs
    -0.73
     ears
    -0.71
     throat
    -0.66
     legs
    -0.66
     CreateTagHelper
    -0.65
    eyes
    -0.65
     throats
    -0.64
     stomach
    -0.63
     limbs
    -0.63
    POSITIVE LOGITS
    앵
    0.38
    дачи
    0.37
    cona
    0.36
    efte
    0.36
    enumii
    0.35
    UrlResolution
    0.35
     Verr
    0.35
    yntaxException
    0.35
    raulic
    0.34
     OGSÅ
    0.34
    Act Density 0.068%

    No Known Activations