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

    Neuronpedia

    INDEX
    Explanations

    character names or titles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorable
    -0.22
     colorful
    -0.21
     Savior
    -0.20
     à¹Ĩ
    -0.19
     analyze
    -0.18
     endeavors
    -0.18
     unfavorable
    -0.18
     honors
    -0.18
     behaviors
    -0.18
     centers
    -0.17
    POSITIVE LOGITS
     Partition
    0.28
     neighbourhood
    0.18
    Partition
    0.18
     labour
    0.18
     metres
    0.17
     neighbours
    0.16
    ursive
    0.15
     ageing
    0.15
     zam
    0.15
    Versions
    0.15
    Act Density 0.044%

    No Known Activations