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

    Neuronpedia

    INDEX
    Explanations

    references to military rank and command structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     social
    -0.52
    pí
    -0.48
    holt
    -0.47
     xã
    -0.47
    p
    -0.46
    getitem
    -0.46
    nien
    -0.45
     die
    -0.45
    ULTURAL
    -0.45
     p
    -0.45
    POSITIVE LOGITS
     itſelf
    0.79
     ―――――
    0.76
     pleaſure
    0.75
     purpoſe
    0.74
     ligiloj
    0.73
     whoſe
    0.73
     ExecuteAsync
    0.72
    ControllerAdvice
    0.72
    ſelf
    0.71
    extAlignment
    0.71
    Act Density 0.162%

    No Known Activations