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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to classifications and identity distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     «
    -0.82
     �
    -0.80
     ãĢĮ
    -0.77
     §§
    -0.68
    ãĢĮ
    -0.66
     Berks
    -0.66
     Administ
    -0.59
     ''
    -0.59
    âĶĢ
    -0.59
     ().
    -0.59
    POSITIVE LOGITS
    "
    1.49
    "?
    1.42
    "!
    1.40
    ",
    1.38
    "-
    1.37
    ")
    1.35
    ".
    1.28
    "—
    1.27
    ";
    1.25
    ").
    1.25
    Act Density 0.307%

    No Known Activations