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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases and key findings in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.05
    +#+#
    -0.92
     Majefty
    -0.91
     doubtnut
    -0.88
     Boles
    -0.83
     itſelf
    -0.80
     estimés
    -0.76
    曖昧さ回避
    -0.75
     Chriftian
    -0.75
     reafon
    -0.73
    POSITIVE LOGITS
     obiec
    0.46
    행
    0.41
     Data
    0.39
    nios
    0.38
     Schicht
    0.38
     interviews
    0.38
     interviewing
    0.38
    getData
    0.38
     éta
    0.38
     .
    0.37
    Act Density 0.381%

    No Known Activations