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

    Neuronpedia

    INDEX
    Explanations

    instances of personal reflection and decision-making statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venes
    -0.15
    noDB
    -0.15
    ropp
    -0.14
    iders
    -0.14
    picture
    -0.14
    _ASSUME
    -0.14
    @qq
    -0.14
    opers
    -0.14
     Oy
    -0.14
    ležit
    -0.14
    POSITIVE LOGITS
    hof
    0.17
    ingo
    0.15
    adero
    0.14
    onto
    0.14
     surely
    0.14
    ackbar
    0.14
    iyet
    0.14
    éĽĨä¸Ń
    0.14
    å¥Ĺ
    0.14
    PPER
    0.14
    Act Density 0.145%

    No Known Activations