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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adverse consequences or controversial issues

    oai_token-act-pair · gpt-3.5-turbo

    elements related to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miche
    -0.89
    ä¿
    -0.86
     Micha
    -0.85
     Carey
    -0.82
     CIS
    -0.81
     Sik
    -0.80
     HTC
    -0.78
     Denis
    -0.78
     Scy
    -0.77
    ĨĴ
    -0.76
    POSITIVE LOGITS
     Ball
    2.18
    Ball
    2.17
     BALL
    2.01
     ball
    1.93
    ball
    1.86
     balls
    1.79
    BALL
    1.75
     Balls
    1.73
    balls
    1.56
     Balloon
    1.47
    Act Density 0.220%

    No Known Activations