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

    Neuronpedia

    INDEX
    Explanations

    references to partner violence and related risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.55
     Robinson
    -0.51
    kais
    -0.50
    XtraBars
    -0.50
    ArgumentParser
    -0.48
    م
    -0.48
     -
    -0.47
     Wilson
    -0.47
     Har
    -0.47
     I
    -0.46
    POSITIVE LOGITS
     scolaires
    0.93
     noires
    0.85
     auroit
    0.84
     sauvages
    0.81
     médicaux
    0.81
     Monfieur
    0.80
     énergétique
    0.78
     上午
    0.78
     ſtand
    0.77
     épais
    0.77
    Act Density 0.177%

    No Known Activations