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

    Neuronpedia

    INDEX
    Explanations

    words related to numerical values or statistical information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'z'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compe
    -0.67
    WAYS
    -0.66
     disadvant
    -0.66
    tenance
    -0.64
     Staples
    -0.63
    HAEL
    -0.63
     outgoing
    -0.63
    ModLoader
    -0.62
    kinson
    -0.60
     Fargo
    -0.59
    POSITIVE LOGITS
    ebra
    1.47
    odiac
    1.29
    ooming
    1.24
    ealous
    1.20
    ipping
    1.18
    eros
    1.17
    ippers
    1.16
    ipped
    1.12
    ippy
    1.10
    ipl
    1.09
    Act Density 0.013%

    No Known Activations