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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives and descriptors that evoke vivid imagery or strong emotional responses

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

    describing adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nôtre
    -0.49
     vœ
    -0.44
     officielles
    -0.42
     normaux
    -0.42
     âme
    -0.40
     réunis
    -0.40
     ainfi
    -0.40
     négatif
    -0.40
     woda
    -0.39
     laiton
    -0.39
    POSITIVE LOGITS
    neurial
    0.69
    AndEndTag
    0.65
     charismatic
    0.65
     enigmatic
    0.64
     ambitious
    0.63
    忑
    0.61
     brutal
    0.61
    bodied
    0.60
     energetic
    0.60
    ggish
    0.60
    Act Density 0.057%

    No Known Activations