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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing personal reactions and opinions about films or books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Untitled
    -0.69
    GEBURTS
    -0.64
    /**
    -0.63
     المعيارى
    -0.63
    ámico
    -0.61
     Exacts
    -0.61
     natin
    -0.60
    ModelAdmin
    -0.59
     HttpHeaders
    -0.59
    Попис
    -0.59
    POSITIVE LOGITS
     enjoyable
    0.85
     enjoyed
    0.73
     excellent
    0.71
     recommend
    0.68
     entertaining
    0.66
     interesting
    0.65
     Loved
    0.64
     fascinating
    0.62
    Enjoyed
    0.62
    excellent
    0.61
    Act Density 0.277%

    No Known Activations