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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain connecting words, indicating relationships or transitions between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.16
    @js
    -0.16
    ober
    -0.16
    .addCell
    -0.15
     ellos
    -0.15
    orners
    -0.15
     ihnen
    -0.15
     respondsToSelector
    -0.15
    ernel
    -0.15
    ingham
    -0.15
    POSITIVE LOGITS
     instead
    0.32
    instead
    0.25
     Instead
    0.23
    Instead
    0.20
     replaced
    0.20
     Gone
    0.20
     gone
    0.19
     except
    0.18
     soon
    0.18
     formerly
    0.17
    Act Density 0.065%

    No Known Activations