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

    Neuronpedia

    INDEX
    Explanations

    references to locations or contexts for various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLUDE
    -0.15
    atham
    -0.15
     hopes
    -0.14
    urat
    -0.14
    arnings
    -0.14
    .market
    -0.13
    ibur
    -0.13
    onet
    -0.13
     ãĤ¢ãĤ¤
    -0.13
    ounder
    -0.13
    POSITIVE LOGITS
     view
    0.25
     details
    0.22
     occasion
    0.21
     virtue
    0.20
     principle
    0.20
     detriment
    0.20
     charge
    0.20
     favour
    0.20
     parallel
    0.19
     front
    0.19
    Act Density 0.166%

    No Known Activations