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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or disclaimers related to arguments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricular
    -0.16
    preneur
    -0.16
    zug
    -0.15
    UnitOfWork
    -0.15
    _ttl
    -0.14
    illet
    -0.14
     جر
    -0.14
     transaction
    -0.14
    ttl
    -0.14
    Ú¯ÛĮرÛĮ
    -0.13
    POSITIVE LOGITS
     speed
    0.30
     Speed
    0.28
    speed
    0.27
    -Speed
    0.26
     speeds
    0.26
    -speed
    0.25
    Speed
    0.24
     records
    0.24
     SPEED
    0.24
    .speed
    0.23
    Act Density 0.000%

    No Known Activations