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

    Neuronpedia

    INDEX
    Explanations

    references to sin and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.94
    ')")
    -0.92
     ―――――
    -0.82
    "):
    -0.78
    PrototypeOf
    -0.77
     Anſ
    -0.77
    PDR
    -0.76
    Зноскі
    -0.76
     Parcelable
    -0.76
    }}}
    -0.75
    POSITIVE LOGITS
     sin
    3.03
     Sin
    2.90
    Sin
    2.81
    sin
    2.80
     SIN
    2.54
    SIN
    2.27
     sins
    2.24
     Sins
    1.94
     sinned
    1.57
     sinful
    1.56
    Act Density 0.063%

    No Known Activations