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

    Neuronpedia

    INDEX
    Explanations

    references to charity and community service initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /MIT
    -0.16
    oure
    -0.14
    acker
    -0.14
    è§ĦåĪĴ
    -0.14
    onta
    -0.14
    rud
    -0.14
    ozo
    -0.14
    cratch
    -0.13
    ine
    -0.13
     Knot
    -0.13
    POSITIVE LOGITS
    ecycle
    0.18
    asma
    0.17
     Salv
    0.16
    ध
    0.16
     cons
    0.16
     Parts
    0.15
     salv
    0.15
    disposed
    0.15
     dumpster
    0.15
     disposed
    0.15
    Act Density 0.222%

    No Known Activations