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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives, particularly in relation to ranking and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vic
    -0.18
    ãĥ¼ãĥ
    -0.17
     Bark
    -0.15
    untu
    -0.15
    cken
    -0.15
     into
    -0.14
    izona
    -0.14
    edith
    -0.14
     spect
    -0.14
    ider
    -0.14
    POSITIVE LOGITS
    udos
    0.16
    èª
    0.15
    mpl
    0.15
    ãĥŃãĥ³
    0.14
    ifter
    0.14
    OrCreate
    0.14
    Lit
    0.14
    owie
    0.14
    linky
    0.14
    sten
    0.13
    Act Density 0.071%

    No Known Activations