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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating progression or movement in terms of distance or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢд
    -0.18
    azer
    -0.17
    .criteria
    -0.16
    ác
    -0.15
    olla
    -0.15
    rack
    -0.15
    ruk
    -0.15
    olls
    -0.15
    _BS
    -0.15
    lore
    -0.14
    POSITIVE LOGITS
     counter
    0.20
     so
    0.19
     beyond
    0.19
     Beyond
    0.17
     contra
    0.17
     contr
    0.16
    VERN
    0.16
     Counter
    0.15
    aad
    0.15
     Mobil
    0.15
    Act Density 0.047%

    No Known Activations