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

    Neuronpedia

    INDEX
    Explanations

    technical data and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "3"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.82
    rolet
    -0.73
    esville
    -0.65
    sym
    -0.63
     mell
    -0.62
     Suzuki
    -0.61
     Winc
    -0.58
    numbered
    -0.58
    trak
    -0.58
     woo
    -0.57
    POSITIVE LOGITS
    rd
    2.01
    RD
    1.18
    DS
    0.96
    dfx
    0.95
    Aren
    0.84
    peat
    0.84
    PO
    0.78
     cheers
    0.78
    sg
    0.77
    DP
    0.77
    Act Density 0.108%

    No Known Activations