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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols indicating data or coding elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Behaviour
    -0.18
     labour
    -0.17
     Behaviour
    -0.17
     humour
    -0.17
     Aluminium
    -0.17
     fucks
    -0.16
     -↵
    -0.16
     harbour
    -0.16
     US
    -0.15
     behaviours
    -0.15
    POSITIVE LOGITS
     pretty
    0.16
     nice
    0.15
    udos
    0.14
    اÙĪÙĬ
    0.14
     --
    0.14
    pretty
    0.14
     fairly
    0.13
    اÙĪ
    0.13
     expansion
    0.13
     probably
    0.13
    Act Density 0.001%

    No Known Activations