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

    Neuronpedia

    INDEX
    Explanations

    instances of formal correspondence or communications, particularly letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apel
    -0.17
    ÃŃg
    -0.17
    elon
    -0.17
    alus
    -0.16
    ancias
    -0.14
    itesse
    -0.14
    öst
    -0.14
    rum
    -0.14
    iquid
    -0.14
    indre
    -0.14
    POSITIVE LOGITS
    ORA
    0.15
    /about
    0.15
    aley
    0.15
     Rena
    0.14
    UDGE
    0.14
     Leap
    0.14
    547
    0.13
    oko
    0.13
    udge
    0.13
     cent
    0.13
    Act Density 0.061%

    No Known Activations