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

    Neuronpedia

    INDEX
    Explanations

    metadata elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħ
    -1.64
    ·¸
    -1.59
    alloc
    -1.48
    timer
    -1.41
     outside
    -1.40
    Ľ
    -1.38
     dies
    -1.36
    Ł
    -1.35
    ĩ
    -1.35
    Set
    -1.35
    POSITIVE LOGITS
     correspondence
    1.77
    ingly
    1.75
    ely
    1.68
    TRODUCTION
    1.50
    eness
    1.49
    ое
    1.49
     aloud
    1.48
    beit
    1.47
    igraphy
    1.44
    ively
    1.43
    Act Density 0.157%

    No Known Activations