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

    Neuronpedia

    INDEX
    Explanations

    unique or singular items within a group or category

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" indicating exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.72
    aptic
    -0.68
    staking
    -0.68
    ategor
    -0.68
    des
    -0.65
    align
    -0.63
    bane
    -0.62
    mass
    -0.61
    MAP
    -0.61
     nep
    -0.61
    POSITIVE LOGITS
     thing
    0.85
     surviving
    0.85
     drawback
    0.82
     conceivable
    0.78
     dissenting
    0.76
     remaining
    0.76
     exception
    0.75
     reason
    0.74
    ONE
    0.72
     recourse
    0.72
    Act Density 0.034%

    No Known Activations