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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns such as measurements or age references

    oai_token-act-pair · gpt-3.5-turbo

    numeric values associated with age or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γ
    -0.76
    essim
    -0.76
    acci
    -0.76
    PDATE
    -0.73
    ĵĺ
    -0.72
    hemy
    -0.70
    iosis
    -0.68
    ãĤ©
    -0.67
    sylv
    -0.66
    OVA
    -0.66
    POSITIVE LOGITS
    ĸļ
    0.72
    576
    0.71
    venth
    0.69
    04
    0.69
    warts
    0.66
    02
    0.65
    10
    0.63
     Mariners
    0.63
    610
    0.63
    678
    0.63
    Act Density 0.214%

    No Known Activations