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

    Neuronpedia

    INDEX
    Explanations

    references to legal charges and judicial proceedings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     manusia
    -0.52
     فريبيس
    -0.49
     aprovechar
    -0.48
     letti
    -0.47
    ubourg
    -0.46
     dalamnya
    -0.45
     giusta
    -0.45
     geboten
    -0.44
     sometimes
    -0.44
    edra
    -0.44
    POSITIVE LOGITS
    abestanden
    0.87
    ValueStyle
    0.87
     pleaſure
    0.83
     houſe
    0.79
     themſelves
    0.75
     itſelf
    0.75
     purpoſe
    0.74
     ſtate
    0.73
     Jefus
    0.72
     cauſe
    0.72
    Act Density 0.159%

    No Known Activations