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

    Neuronpedia

    INDEX
    Explanations

    references to authority or notable institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UDA
    -0.18
    icontrol
    -0.15
    itr
    -0.15
    ollah
    -0.14
     ease
    -0.14
    POSIT
    -0.14
    Overlap
    -0.13
    ÑĢÑĥÑģ
    -0.13
    antan
    -0.13
    .localization
    -0.13
    POSITIVE LOGITS
    -of
    0.50
     Of
    0.29
     OF
    0.27
    _of
    0.27
    Of
    0.27
    _Of
    0.26
    _OF
    0.25
     à¤ijफ
    0.21
     fo
    0.21
    .of
    0.17
    Act Density 0.179%

    No Known Activations