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

    Neuronpedia

    INDEX
    Explanations

    words related to draining, depletion, and extraction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.64
    rungsseite
    -0.63
     שוליים
    -0.62
    /**
    -0.60
     Италијани
    -0.60
    verwijspagina
    -0.58
    instancetype
    -0.56
    RectangleBorder
    -0.56
    onedDateTime
    -0.56
    marck
    -0.56
    POSITIVE LOGITS
     drained
    1.14
     draining
    1.05
     drain
    0.95
    drained
    0.89
     drains
    0.89
     Drain
    0.83
    Drain
    0.82
    drain
    0.82
     deple
    0.76
     DRAIN
    0.73
    Act Density 0.325%

    No Known Activations