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

    Neuronpedia

    INDEX
    Explanations

    special characters, likely non-standard line breaks

    oai_token-act-pair · gpt-3.5-turbo

    instances of urgency or critical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citiz
    -0.80
     footing
    -0.75
    naissance
    -0.71
    cius
    -0.68
     undermin
    -0.67
    ¥ŀ
    -0.63
    hement
    -0.62
    aditional
    -0.61
     exha
    -0.60
    etheless
    -0.60
    POSITIVE LOGITS
    Eventually
    1.09
    Then
    1.00
    Later
    0.99
    ³³³³
    0.97
    ³³³³³³³³
    0.92
    DragonMagazine
    0.89
    Bus
    0.85
    Suddenly
    0.85
    ³³³
    0.85
    Scroll
    0.84
    Act Density 0.412%

    No Known Activations