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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "crusader" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    393
    -0.17
    SKTOP
    -0.16
    787
    -0.16
    394
    -0.15
     practical
    -0.15
     tratt
    -0.15
    isay
    -0.15
    creds
    -0.14
    719
    -0.14
    casts
    -0.14
    POSITIVE LOGITS
    ifix
    0.36
    aders
    0.28
    ader
    0.23
    -fontawesome
    0.19
     cruc
    0.19
    ified
    0.19
    ible
    0.18
    iform
    0.18
    fix
    0.18
    iaux
    0.17
    Act Density 0.005%

    No Known Activations