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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing clarity or certainty in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ulang
    -0.54
     Marsden
    -0.53
    findall
    -0.53
    ech
    -0.52
     chargés
    -0.52
    umi
    -0.52
    ZIN
    -0.51
    ddagger
    -0.51
     mandiri
    -0.50
    chin
    -0.49
    POSITIVE LOGITS
     obvious
    1.53
    obvious
    1.47
    VIOUS
    1.40
    Obvious
    1.37
     obvio
    1.23
     obviously
    1.17
     evident
    1.17
    evident
    1.16
    obviously
    1.15
     évident
    1.14
    Act Density 0.141%

    No Known Activations