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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the status or existence of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _defs
    -0.16
     Leh
    -0.15
    ohn
    -0.15
    vale
    -0.14
    tec
    -0.14
    kee
    -0.13
    _ASSUME
    -0.13
    à¹Ĥà¸Ľ
    -0.13
    otta
    -0.13
     Rog
    -0.13
    POSITIVE LOGITS
    cher
    0.17
    è¼
    0.16
     hasn
    0.14
    udur
    0.14
    ')['
    0.14
     magnets
    0.14
    Insurance
    0.13
    (Sender
    0.13
    icap
    0.13
     Magnet
    0.13
    Act Density 0.001%

    No Known Activations