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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe intensity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.46
    <eos>
    -0.45
     he
    -0.44
     &&
    -0.43
     године
    -0.42
     so
    -0.42
    (
    -0.40
    ResumeLayout
    -0.39
    So
    -0.38
    !
    -0.38
    POSITIVE LOGITS
     myſelf
    1.06
    ^(@)
    1.00
     raiſ
    1.00
     leſs
    0.99
     Monfieur
    0.99
     reaſon
    0.97
     pleaſure
    0.94
    ſelf
    0.93
     Reſ
    0.92
     themſelves
    0.92
    Act Density 0.700%

    No Known Activations