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

    Neuronpedia

    INDEX
    Explanations

    relationships involving design and planning requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãħ
    -0.18
    30
    -0.15
    auc
    -0.14
    192
    -0.14
    50
    -0.14
    chen
    -0.14
     Å
    -0.14
    786
    -0.13
    ahr
    -0.13
    alog
    -0.13
    POSITIVE LOGITS
    ¡
    0.21
    £
    0.19
    Ń
    0.17
    ŀ
    0.15
    -valu
    0.15
    ³
    0.15
    avor
    0.15
    ÑĨÑĮ
    0.15
    ibold
    0.15
    質
    0.14
    Act Density 0.418%

    No Known Activations