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

    Neuronpedia

    INDEX
    Explanations

    sequences related to voting in a ranking or poll context

    oai_token-act-pair · gpt-3.5-turbo

    references to votes or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omorphic
    -0.58
    yout
    -0.57
     favor
    -0.52
    conom
    -0.52
    ãĥķãĤ©
    -0.51
     coh
    -0.51
    Reloaded
    -0.50
    nen
    -0.48
     fences
    -0.47
    20439
    -0.46
    POSITIVE LOGITS
    onga
    0.52
     TBD
    0.50
     TBA
    0.46
    ucer
    0.46
     Valkyrie
    0.45
     Ibid
    0.45
    hovah
    0.45
     Extras
    0.45
    endif
    0.44
     Destination
    0.44
    Act Density 0.746%

    No Known Activations