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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or expressing skepticism about commonly held beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -0.16
    endor
    -0.15
    umer
    -0.15
    lew
    -0.15
    visor
    -0.14
     sinon
    -0.14
    -addons
    -0.14
    ány
    -0.14
    uat
    -0.14
    agua
    -0.14
    POSITIVE LOGITS
    true
    0.21
     true
    0.21
     fine
    0.17
    True
    0.16
     True
    0.15
     interesting
    0.15
     instruct
    0.15
     overs
    0.15
     perfectly
    0.15
     partially
    0.15
    Act Density 0.279%

    No Known Activations