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

    Neuronpedia

    INDEX
    Explanations

    quotes and statements made by people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to people's names and their roles or positions in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whilst
    -1.00
    ".[
    -0.91
     Whilst
    -0.84
    ONDON
    -0.79
    !".
    -0.78
    ÙĪ
    -0.77
    Ú
    -0.76
    Äĩ
    -0.75
    Ð
    -0.74
    Âł
    -0.74
    POSITIVE LOGITS
     spokeswoman
    1.12
     spokesman
    0.92
     attorney
    0.85
     supervisors
    0.84
     attorneys
    0.83
     Sgt
    0.82
     troopers
    0.80
     sheriff
    0.78
     Legislature
    0.78
     county
    0.77
    Act Density 0.938%

    No Known Activations