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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making and preference evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contri
    -0.19
    ymous
    -0.15
    iples
    -0.15
    NECT
    -0.14
     switch
    -0.14
    annah
    -0.14
     Sinn
    -0.13
    ÅĤaw
    -0.13
     Region
    -0.13
    anny
    -0.13
    POSITIVE LOGITS
    uble
    0.16
    elson
    0.16
    bil
    0.15
     useForm
    0.15
    ihan
    0.15
    Ñĩил
    0.15
     bul
    0.15
    anner
    0.14
    ople
    0.14
    åļ
    0.14
    Act Density 0.067%

    No Known Activations