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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action or engagement in the context of discussions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĢÑĪ
    -0.15
     Ul
    -0.15
    oken
    -0.14
    -el
    -0.14
     prob
    -0.14
     Dance
    -0.14
    azi
    -0.13
    dl
    -0.13
    elon
    -0.13
     Tanner
    -0.13
    POSITIVE LOGITS
    erule
    0.17
    .ToShort
    0.17
    ÙĦاÙĨ
    0.17
    IBE
    0.16
    eway
    0.16
    ìĨIJ
    0.15
    óc
    0.15
    illance
    0.15
     Mvc
    0.14
    (éĩij
    0.14
    Act Density 0.001%

    No Known Activations