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

    Neuronpedia

    INDEX
    Explanations

    words related to equality or similarity

    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
    ASE
    -0.75
     Origins
    -0.70
    glers
    -0.70
    liest
    -0.68
     Liang
    -0.65
    WARD
    -0.65
     Journals
    -0.64
    ocene
    -0.63
    scape
    -0.63
     Coff
    -0.63
    POSITIVE LOGITS
     situated
    1.02
     spaced
    0.96
    imilar
    0.89
     sized
    0.86
     minded
    0.85
     applicable
    0.84
    inguishable
    0.81
     opposed
    0.79
    osite
    0.79
    etrical
    0.77
    Act Density 0.013%

    No Known Activations