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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledi
    -0.17
    ero
    -0.15
    umd
    -0.14
    erve
    -0.14
    lette
    -0.14
    itas
    -0.14
    erves
    -0.14
    aty
    -0.14
    idad
    -0.14
    ona
    -0.14
    POSITIVE LOGITS
     least
    0.25
    least
    0.18
     how
    0.18
    lassian
    0.18
    Least
    0.18
    tract
    0.18
     closely
    0.17
     sao
    0.16
    cha
    0.15
     ease
    0.15
    Act Density 0.051%

    No Known Activations