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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating criticism or condemnation of exploitation and dishonesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profesional
    -0.55
     actores
    -0.52
     Actors
    -0.49
     actors
    -0.49
     Music
    -0.49
     concerts
    -0.48
     profissionais
    -0.48
    Representation
    -0.47
     professional
    -0.46
     profesionales
    -0.46
    POSITIVE LOGITS
     propOrder
    0.88
     صوتيه
    0.86
     TestBed
    0.86
    Искәрмәләр
    0.82
     تانيه
    0.80
     חיצוניים
    0.77
    ьаж
    0.76
     synth
    0.76
     disambiguazione
    0.75
    +#+#
    0.74
    Act Density 0.113%

    No Known Activations