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

    Neuronpedia

    INDEX
    Explanations

    uncommon special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol repeated throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.77
     sled
    -0.68
     unmarked
    -0.65
     marker
    -0.62
     Bunny
    -0.62
     scene
    -0.61
     shroud
    -0.61
    racuse
    -0.61
     Naz
    -0.60
     cottage
    -0.59
    POSITIVE LOGITS
    ¬
    1.04
    ¹
    0.92
    ISIS
    0.89
    ¾
    0.85
    votes
    0.85
    £
    0.82
    º
    0.82
    agree
    0.81
    ½
    0.78
    drivers
    0.78
    Act Density 0.258%

    No Known Activations