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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion or a transition to a new topic

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or symbols indicating emphasis or a statement's strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agric
    -0.78
     ropes
    -0.74
     seiz
    -0.71
     horizont
    -0.69
     Gan
    -0.68
     Mechdragon
    -0.65
     Marshal
    -0.65
     Palest
    -0.63
     Participant
    -0.63
    çīĪ
    -0.62
    POSITIVE LOGITS
    Ĵ
    1.04
    ķ
    0.99
    º
    0.98
    ¹
    0.96
    ¢
    0.92
    ¡
    0.92
    ®
    0.90
    ª
    0.90
    £
    0.89
    ·
    0.88
    Act Density 0.072%

    No Known Activations