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

    Neuronpedia

    INDEX
    Explanations

    unique characters or symbols such as "Ċ" or "âĢ" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of alarming or significant news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.94
     tremend
    -0.85
     eleph
    -0.83
    ò
    -0.81
    aditional
    -0.80
     exha
    -0.78
     occas
    -0.76
     practition
    -0.75
     exting
    -0.74
     councill
    -0.73
    POSITIVE LOGITS
    Í
    0.78
    ̶
    0.71
    Merit
    0.71
    rou
    0.69
    Correct
    0.67
    rosso
    0.66
    使
    0.66
    ãĥ¯ãĥ³
    0.66
    1016
    0.64
    ³³³
    0.63
    Act Density 0.670%

    No Known Activations