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

    Neuronpedia

    INDEX
    Explanations

    direct quotations and speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.71
    ’
    -1.61
     ‘
    -1.59
    ”
    -1.50
    ’,
    -1.42
    .’
    -1.38
    .”
    -1.36
    ’.
    -1.34
    “
    -1.31
    ”,
    -1.28
    POSITIVE LOGITS
     -"
    1.43
    ^(@)
    1.35
     Jefus
    1.35
    。"
    1.34
     Efq
    1.32
     ...'
    1.27
     purpoſe
    1.25
     poffible
    1.25
     Majefty
    1.24
    ...'
    1.23
    Act Density 1.120%

    No Known Activations