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

    Neuronpedia

    INDEX
    Explanations

    programmatic syntax elements and formatting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĥÑħ
    -0.15
    ãĥ¼ãĥģ
    -0.14
    pton
    -0.14
    째
    -0.14
    _argv
    -0.14
    kte
    -0.14
     gros
    -0.13
     Stamford
    -0.13
     Agility
    -0.13
     èIJ
    -0.13
    POSITIVE LOGITS
    ÄįÃŃ
    0.16
    åŁº
    0.15
    266
    0.15
    ser
    0.14
     disarm
    0.14
    action
    0.14
    .kode
    0.14
    帽
    0.14
     Combination
    0.14
    Į
    0.14
    Act Density 0.011%

    No Known Activations