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

    Neuronpedia

    INDEX
    Explanations

    narratives involving conflict and resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estão
    -0.18
     podem
    -0.17
     possono
    -0.17
     hacen
    -0.16
     hanno
    -0.15
    oken
    -0.15
    tie
    -0.15
     são
    -0.14
    SEN
    -0.14
     vede
    -0.14
    POSITIVE LOGITS
     tu
    0.39
     fue
    0.33
    tu
    0.30
    Tu
    0.29
     se
    0.29
     Tu
    0.29
     dio
    0.28
     pudo
    0.25
     hizo
    0.23
    dio
    0.23
    Act Density 0.045%

    No Known Activations