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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to safety and risk management in engineering and business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipher
    -0.19
     Cord
    -0.17
     Cipher
    -0.16
     coco
    -0.16
     canv
    -0.16
     Cater
    -0.15
     Conway
    -0.15
     Cair
    -0.15
    _xs
    -0.15
    æ¥
    -0.15
    POSITIVE LOGITS
     critical
    0.63
    crit
    0.61
     Crit
    0.60
     krit
    0.60
     crit
    0.59
    critical
    0.59
     кÑĢиÑĤ
    0.57
     critic
    0.57
    Crit
    0.57
     Critical
    0.56
    Act Density 0.097%

    No Known Activations