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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "philosophy" and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pb
    -0.16
    è®®
    -0.15
    izona
    -0.15
     Dil
    -0.14
    orce
    -0.14
    poÄį
    -0.14
    ôm
    -0.14
    arb
    -0.13
    WISE
    -0.13
     Vak
    -0.13
    POSITIVE LOGITS
    okin
    0.15
     Fuse
    0.15
    /System
    0.14
    ippet
    0.14
    aupt
    0.14
    ically
    0.14
    stinian
    0.14
    رÛĮÚ©
    0.13
    bens
    0.13
    enger
    0.13
    Act Density 0.014%

    No Known Activations