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

    Neuronpedia

    INDEX
    Explanations

    words related to selecting and choosing options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esh
    -0.16
    ãģıãĤĵ
    -0.15
    .fre
    -0.15
    ald
    -0.15
    elden
    -0.14
    utils
    -0.14
     dau
    -0.14
    ilot
    -0.14
    adder
    -0.14
     honor
    -0.14
    POSITIVE LOGITS
     desired
    0.26
    desired
    0.21
     Tro
    0.17
    Fal
    0.17
     Desired
    0.16
     Jarvis
    0.16
    æĥ³è¦ģ
    0.15
    tro
    0.15
    @js
    0.15
     desire
    0.15
    Act Density 0.047%

    No Known Activations