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
     bouche
    -0.72
     houſe
    -0.71
     termica
    -0.71
    itudinal
    -0.67
     asiatique
    -0.66
     médié
    -0.64
     ſche
    -0.63
     Caballero
    -0.63
    ⓘ
    -0.62
     midline
    -0.62
    POSITIVE LOGITS
    bardziej
    1.04
     very
    0.99
     most
    0.95
     πιο
    0.94
     more
    0.87
     meest
    0.79
     πολύ
    0.78
     наиболее
    0.77
    иболее
    0.76
     Very
    0.76
    Act Density 0.303%

    No Known Activations