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

    Neuronpedia

    INDEX
    Explanations

    references to "Lo" and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uz
    -0.15
    byt
    -0.15
    /loose
    -0.14
    /left
    -0.14
    ÏĥÏĦα
    -0.14
    uyu
    -0.14
    uja
    -0.14
    umno
    -0.14
    illed
    -0.14
     needless
    -0.14
    POSITIVE LOGITS
    fty
    0.25
    ewe
    0.23
    ew
    0.23
    UIS
    0.22
    oney
    0.21
    zano
    0.20
    ews
    0.20
    eb
    0.20
    fts
    0.20
    oser
    0.19
    Act Density 0.008%

    No Known Activations