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

    Neuronpedia

    INDEX
    Explanations

    the use of openers or introductory phrases in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.83
    y
    -0.79
     "
    -0.76
    p
    -0.72
     *
    -0.71
    n
    -0.67
     .
    -0.65
    b
    -0.64
     blo
    -0.64
    tg
    -0.63
    POSITIVE LOGITS
     myſelf
    1.83
     itſelf
    1.80
     themſelves
    1.64
     pleaſure
    1.61
     Jefus
    1.59
     becauſe
    1.57
     himſelf
    1.57
     Reſ
    1.51
    ſelf
    1.49
     Majefty
    1.48
    Act Density 0.017%

    No Known Activations