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

    Neuronpedia

    INDEX
    Explanations

    comparative terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "equally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.73
    ocene
    -0.73
    uese
    -0.72
     Tie
    -0.70
     Coff
    -0.66
     Buy
    -0.65
    ourke
    -0.65
     Vu
    -0.65
     Jackets
    -0.64
    Query
    -0.64
    POSITIVE LOGITS
     sized
    1.01
     situated
    0.93
     weighted
    0.89
     spaced
    0.89
     applicable
    0.89
     important
    0.88
     impressive
    0.83
     adept
    0.83
     emph
    0.81
     nause
    0.80
    Act Density 0.026%

    No Known Activations