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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    θÎŃ
    -0.14
    ÑĥÑĢÑĥ
    -0.14
     Or
    -0.14
    amil
    -0.14
     E
    -0.13
    ushman
    -0.13
     Bo
    -0.13
     fan
    -0.13
    archives
    -0.13
     rival
    -0.13
    POSITIVE LOGITS
     nack
    0.16
     addCriterion
    0.16
     endors
    0.15
    ÑıÑĩ
    0.15
    OTA
    0.15
    ernel
    0.15
    anches
    0.14
    .twig
    0.14
    arella
    0.14
     instruct
    0.14
    Act Density 0.106%

    No Known Activations