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

    Neuronpedia

    INDEX
    Explanations

    non-English language words or characters

    oai_token-act-pair · gpt-3.5-turbo

    various types of numerical and coded sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.62
     Canaver
    -0.61
    onnaissance
    -0.50
    Rule
    -0.49
     seiz
    -0.49
     Lerner
    -0.49
    iets
    -0.48
    estern
    -0.47
    urion
    -0.47
    paio
    -0.47
    POSITIVE LOGITS
    .).
    0.96
    '.
    0.83
    )).
    0.82
     respectively
    0.81
    %.
    0.81
    !.
    0.81
    ''.
    0.75
    '."
    0.73
    .'"
    0.72
    $.
    0.72
    Act Density 1.670%

    No Known Activations