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

    Neuronpedia

    INDEX
    Explanations

    statements associated with recommendations and the potential outcomes of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emaker
    -0.15
    ãģĮãģĬ
    -0.14
    _FOREACH
    -0.14
    ueling
    -0.14
    :NS
    -0.14
    boxed
    -0.14
    Äħż
    -0.14
     Fork
    -0.14
     apart
    -0.14
    cio
    -0.13
    POSITIVE LOGITS
    .fhir
    0.16
    aucoup
    0.16
    ware
    0.15
    .gdx
    0.15
    ModelError
    0.15
    .scalablytyped
    0.14
    637
    0.13
    /aws
    0.13
    oplevel
    0.13
    centration
    0.13
    Act Density 0.459%

    No Known Activations