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

    Neuronpedia

    INDEX
    Explanations

    the phrase "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .decorate
    -0.16
    еÑĢов
    -0.15
    áh
    -0.15
    uitka
    -0.15
    à¤Łà¤°
    -0.15
    iller
    -0.14
    _UNUSED
    -0.14
     anlamına
    -0.14
    ComputedStyle
    -0.14
    RLF
    -0.14
    POSITIVE LOGITS
     fraction
    0.23
     price
    0.23
     less
    0.22
     only
    0.22
     prices
    0.21
     penn
    0.21
     fractions
    0.20
     Less
    0.19
     mere
    0.19
    prices
    0.18
    Act Density 0.042%

    No Known Activations