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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various concepts and themes represented by symbols and metaphors rather than direct language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.82
     ABE
    -0.71
     Squirrel
    -0.67
     Statistics
    -0.65
    ulkan
    -0.65
     federation
    -0.64
     juggling
    -0.63
     Rag
    -0.62
     detached
    -0.62
     Shroud
    -0.60
    POSITIVE LOGITS
    ł
    1.14
    ¹
    1.06
    IJ
    1.05
    Ķ
    1.03
    ª
    1.00
    Ĵ
    0.99
    «
    0.95
    ¬
    0.94
    Ń
    0.94
    ³
    0.92
    Act Density 0.081%

    No Known Activations