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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities and categories, likely in a technical or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledge
    -0.16
    _OW
    -0.16
    uggage
    -0.16
     kalp
    -0.16
     Fauc
    -0.15
    adult
    -0.15
    Rocket
    -0.15
     Adult
    -0.14
    еÑĢж
    -0.14
    SystemService
    -0.14
    POSITIVE LOGITS
     productivity
    0.19
     operator
    0.18
     Heavy
    0.18
     trailer
    0.17
    tracked
    0.17
     job
    0.16
    Heavy
    0.16
     Job
    0.16
     tracked
    0.16
     heavy
    0.16
    Act Density 0.059%

    No Known Activations