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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative forms of adjectives and adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pyx
    -0.15
    InBackground
    -0.15
    ãĥĶãĥ¼
    -0.15
    kv
    -0.15
    æ¥
    -0.14
    ongs
    -0.14
    pent
    -0.13
    ency
    -0.13
     Vor
    -0.13
    pedia
    -0.13
    POSITIVE LOGITS
    ollen
    0.16
    asaki
    0.15
    irm
    0.15
    OwnProperty
    0.14
    amed
    0.14
    @student
    0.14
    redo
    0.14
    umlu
    0.14
    _drv
    0.14
    ird
    0.13
    Act Density 0.032%

    No Known Activations