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

    Neuronpedia

    INDEX
    Explanations

    superlative forms of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.16
     St
    -0.15
    548
    -0.15
    ách
    -0.14
    argv
    -0.14
    áj
    -0.14
    ket
    -0.14
     gears
    -0.13
    GI
    -0.13
     den
    -0.13
    POSITIVE LOGITS
    uso
    0.16
    åİħ
    0.15
     atIndex
    0.15
    erm
    0.15
    /packages
    0.15
    uni
    0.15
    enko
    0.14
    udos
    0.14
    mus
    0.14
    reck
    0.14
    Act Density 0.001%

    No Known Activations