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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate suggestions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.17
    651
    -0.17
    oose
    -0.15
    wert
    -0.15
     Tou
    -0.14
    uran
    -0.14
    evin
    -0.14
    ÂŃi
    -0.14
    hammer
    -0.14
    compression
    -0.14
    POSITIVE LOGITS
    orent
    0.16
    eller
    0.15
    lesh
    0.15
     Gle
    0.15
     STREET
    0.15
    ampo
    0.14
    ÑĢÑĮ
    0.14
     suy
    0.14
    abinet
    0.14
     extingu
    0.14
    Act Density 0.042%

    No Known Activations