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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases related to time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phosa
    -0.66
    mide
    -0.63
     Aprove
    -0.55
    Portale
    -0.52
    segno
    -0.51
     venuto
    -0.51
     Biôgrafia
    -0.50
    elesai
    -0.50
    úrate
    -0.49
     spalle
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.95
    Sklici
    0.85
     تانيه
    0.71
    — 
    0.71
    Архівовано
    0.70
    InjectAttribute
    0.63
     forKey
    0.61
    tonsoft
    0.60
    Izvori
    0.60
    </tfoot>
    0.60
    Act Density 0.699%

    No Known Activations