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

    Neuronpedia

    INDEX
    Explanations

    words related to predictions or forecasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eko
    -0.18
    aret
    -0.16
    eenth
    -0.16
    ês
    -0.16
    bedo
    -0.15
    culate
    -0.15
    antly
    -0.15
    /watch
    -0.14
    er
    -0.14
    een
    -0.14
    POSITIVE LOGITS
    nis
    0.24
    icable
    0.20
    icated
    0.19
    ators
    0.18
    acious
    0.17
    ile
    0.17
    stav
    0.17
    atory
    0.17
    abric
    0.16
    snap
    0.16
    Act Density 0.006%

    No Known Activations