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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nes
    -0.15
     både
    -0.15
    sWith
    -0.15
    Ïĥα
    -0.15
    acco
    -0.14
    spir
    -0.14
    sci
    -0.14
     każ
    -0.14
    Ìĥ
    -0.14
    adel
    -0.14
    POSITIVE LOGITS
    /or
    0.25
    -than
    0.23
     directly
    0.19
    wel
    0.19
    anges
    0.18
    ipse
    0.18
    /all
    0.17
     side
    0.17
    phans
    0.17
     alone
    0.16
    Act Density 0.030%

    No Known Activations