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

    Neuronpedia

    INDEX
    Explanations

    references to data structures or syntactical elements in programming or computer code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    footnote or reference markers in academic and technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.77
     gyhoeddwyd
    -0.46
    Parcelize
    -0.45
    UnknownFieldSet
    -0.40
     Roskov
    -0.40
    Carriera
    -0.39
     nil
    -0.39
    JAXB
    -0.38
    ByVersion
    -0.38
     зо
    -0.37
    POSITIVE LOGITS
    toxicity
    0.62
     betweenstory
    0.56
    AndEndTag
    0.52
    nezeu
    0.48
     pulsera
    0.46
     referrerpolicy
    0.46
     distanciation
    0.46
    pholes
    0.45
     betrek
    0.45
     oč
    0.45
    Act Density 0.015%

    No Known Activations