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

    Neuronpedia

    INDEX
    Explanations

    phrases and references that convey personal connection and relational dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plazos
    -0.42
     colegios
    -0.34
     demás
    -0.31
     agujas
    -0.30
     during
    -0.30
     Straß
    -0.29
     iluminação
    -0.28
     contenedores
    -0.28
     ordres
    -0.28
     lycée
    -0.27
    POSITIVE LOGITS
    <unused41>
    0.88
    [@BOS@]
    0.88
    <unused80>
    0.88
    <pad>
    0.88
    <unused74>
    0.88
    <unused17>
    0.87
    <unused28>
    0.87
    <unused14>
    0.87
    <unused3>
    0.87
    <unused8>
    0.87
    Act Density 0.009%

    No Known Activations