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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative forms of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĽ´å¤ļ
    -0.20
     more
    -0.20
    ivec
    -0.17
     mais
    -0.16
    visor
    -0.16
    ilight
    -0.15
     æĽ´
    -0.15
    trys
    -0.15
     более
    -0.15
    ãĤĤãģĨ
    -0.15
    POSITIVE LOGITS
     than
    0.45
    than
    0.35
    -than
    0.35
    _than
    0.28
    Than
    0.27
     THAN
    0.26
     Than
    0.26
     niż
    0.24
     än
    0.24
     importantly
    0.24
    Act Density 0.227%

    No Known Activations