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

    Neuronpedia

    INDEX
    Explanations

    words related to selecting or choosing from a list of options

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating selection or choice among options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.81
    rower
    -0.74
     fid
    -0.71
    ammed
    -0.71
    ario
    -0.70
    culosis
    -0.70
    ivation
    -0.70
    raviolet
    -0.69
    umption
    -0.67
    ended
    -0.66
    POSITIVE LOGITS
     among
    0.87
     amongst
    0.86
     favourites
    0.79
    Ĭ±
    0.79
     randomly
    0.78
     scratch
    0.78
     assorted
    0.78
     innumerable
    0.75
     random
    0.74
     myriad
    0.72
    Act Density 0.131%

    No Known Activations