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

    Neuronpedia

    INDEX
    Explanations

    specific names of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions or impactful statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Secondly
    -0.97
     Secondly
    -0.91
     Whilst
    -0.89
     [+
    -0.88
     independ
    -0.88
     whilst
    -0.83
    âĹ¼
    -0.82
    Furthermore
    -0.82
    theless
    -0.82
    :-
    -0.79
    POSITIVE LOGITS
     POLITICO
    0.88
     NASCAR
    0.80
    Welcome
    0.78
     baseball
    0.73
    LOS
    0.73
    toggle
    0.71
     Rockies
    0.70
     Indianapolis
    0.69
     Amtrak
    0.68
     Baseball
    0.68
    Act Density 1.034%

    No Known Activations