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
    çķ
    -0.17
    .ssl
    -0.16
    andler
    -0.16
    ilip
    -0.15
    owler
    -0.15
    cip
    -0.15
    enberg
    -0.14
    æı
    -0.14
    126
    -0.14
    incinn
    -0.14
    POSITIVE LOGITS
    .gf
    0.18
    SFML
    0.14
    νÏĦ
    0.14
    >tag
    0.14
    VRT
    0.13
    aghetti
    0.13
     Bat
    0.13
    ῦ
    0.13
    Sizer
    0.13
    zdy
    0.13
    Act Density 0.088%

    No Known Activations