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

    Neuronpedia

    INDEX
    Explanations

    questions directed at the reader

    oai_token-act-pair · gpt-3.5-turbo

    questions directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.69
    ylum
    -0.64
    Lenin
    -0.63
    artifacts
    -0.63
     Flags
    -0.60
     Hours
    -0.59
     textbooks
    -0.58
     Shaw
    -0.57
     shotguns
    -0.57
    76561
    -0.55
    POSITIVE LOGITS
     afford
    0.89
     conceive
    0.83
     imagine
    0.83
     reconcile
    0.80
     safely
    0.79
     accommodate
    0.78
    uate
    0.78
    reach
    0.78
     tell
    0.77
    taboola
    0.77
    Act Density 0.036%

    No Known Activations