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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     now
    -0.24
     maintenant
    -0.19
    ongo
    -0.17
     Bulk
    -0.17
    atti
    -0.16
     NOW
    -0.16
    now
    -0.16
    eros
    -0.15
     ÑĤепеÑĢÑĮ
    -0.15
     Now
    -0.15
    POSITIVE LOGITS
    odium
    0.16
     originally
    0.16
    cheon
    0.16
    chedulers
    0.15
    afi
    0.15
    abi
    0.15
    steen
    0.15
    .NaN
    0.14
    origin
    0.14
    slaught
    0.14
    Act Density 0.234%

    No Known Activations