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

    Neuronpedia

    INDEX
    Explanations

    descriptors of relaxed, easygoing, and friendly atmospheres or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipsis
    -0.15
    æ¡IJ
    -0.15
    stim
    -0.15
    acro
    -0.15
    orpion
    -0.14
    gil
    -0.14
     pii
    -0.14
    Advertisement
    -0.14
    lap
    -0.14
    Ú¯ÙĪ
    -0.14
    POSITIVE LOGITS
    okus
    0.17
    _endian
    0.15
     friendly
    0.15
     Fog
    0.14
    ackbar
    0.14
    éĩ
    0.14
    égor
    0.14
    kü
    0.14
    imenti
    0.14
    ÏĦο
    0.14
    Act Density 0.198%

    No Known Activations