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

    Neuronpedia

    INDEX
    Explanations

    mentions of the number "100"

    oai_token-act-pair · gpt-3.5-turbo

    references to "100 percent" or other related numeric guarantees and certainty expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.75
    rift
    -0.74
    achi
    -0.69
    olas
    -0.68
     vigil
    -0.64
    igham
    -0.62
    lihood
    -0.62
    worldly
    -0.61
    oles
    -0.61
     agitation
    -0.60
    POSITIVE LOGITS
    00000
    1.21
    %"
    1.16
    %
    1.10
    %;
    1.05
    Percent
    1.05
    Hz
    1.01
    percent
    0.99
    %]
    0.99
    %:
    0.97
    Mbps
    0.97
    Act Density 0.079%

    No Known Activations