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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the availability and presentation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Identified
    -0.15
     Allowed
    -0.15
    ott
    -0.14
    æ¶Ī
    -0.14
    _ALLOWED
    -0.14
     доп
    -0.14
     ga
    -0.14
    540
    -0.14
    ATEST
    -0.13
    atest
    -0.13
    POSITIVE LOGITS
     available
    0.20
    available
    0.19
     below
    0.18
     provided
    0.17
     posted
    0.17
     contained
    0.16
     furnished
    0.16
    ushman
    0.16
    iska
    0.16
    appa
    0.15
    Act Density 0.085%

    No Known Activations