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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating presence or return

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     felicitación
    -0.44
     Geheimnis
    -0.38
     réussite
    -0.38
     beroep
    -0.36
     Betrachtung
    -0.36
     dúvidas
    -0.36
     adentro
    -0.36
    mbangan
    -0.36
     senhora
    -0.35
     esfuerzan
    -0.35
    POSITIVE LOGITS
     Coming
    0.68
    comes
    0.66
     cometh
    0.66
    Came
    0.66
     arrival
    0.66
    Coming
    0.65
     datang
    0.65
     Arrival
    0.64
     came
    0.63
     Came
    0.63
    Act Density 0.411%

    No Known Activations