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

    Neuronpedia

    INDEX
    Explanations

    references to specific audiences and their interests or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    úde
    -0.15
    üh
    -0.15
    richText
    -0.15
     navr
    -0.15
    eus
    -0.15
    _OCCURRED
    -0.15
    interop
    -0.14
    esome
    -0.14
    WF
    -0.14
    ýn
    -0.14
    POSITIVE LOGITS
     should
    0.32
     can
    0.29
    should
    0.26
     shouldn
    0.22
    Should
    0.22
     Should
    0.22
     must
    0.21
     ought
    0.21
     SHOULD
    0.19
     please
    0.19
    Act Density 0.233%

    No Known Activations