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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives indicating extremes or degrees of comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.17
    isher
    -0.17
    allet
    -0.16
     enough
    -0.16
    üçük
    -0.15
    umat
    -0.15
    ish
    -0.15
    THR
    -0.15
    usic
    -0.14
    erap
    -0.14
    POSITIVE LOGITS
    -ever
    0.31
    -than
    0.23
    ablish
    0.23
     possible
    0.23
     Possible
    0.20
    possible
    0.20
     ever
    0.19
    -known
    0.18
    -selling
    0.18
     possÃŃvel
    0.17
    Act Density 0.063%

    No Known Activations