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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing certainty and assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    642
    -0.15
    entifier
    -0.15
    rzy
    -0.14
    ucz
    -0.14
    nila
    -0.13
    quence
    -0.13
    ondon
    -0.13
    ÑĪив
    -0.13
    áky
    -0.13
    .Îł
    -0.13
    POSITIVE LOGITS
     doubt
    0.96
     Doub
    0.69
     doubts
    0.51
     doubted
    0.48
     doub
    0.45
    oub
    0.40
    oubtedly
    0.39
    çĸij
    0.37
     Ñģом
    0.34
     doubtful
    0.30
    Act Density 0.076%

    No Known Activations