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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similarities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or examples introduced by the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icter
    -0.80
    itiz
    -0.79
    ombat
    -0.78
    ifest
    -0.78
    enary
    -0.73
    elf
    -0.73
    idates
    -0.68
    reth
    -0.68
    erb
    -0.67
    ribution
    -0.67
    POSITIVE LOGITS
    lihood
    1.07
     ours
    0.79
    lier
    0.75
    minded
    0.70
     inher
    0.68
     preferring
    0.67
    liest
    0.67
     evidenced
    0.66
     grouping
    0.62
     ATK
    0.62
    Act Density 0.081%

    No Known Activations