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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive adjectives in the context of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.87
    Sigue
    -0.55
     Sense
    -0.51
    MultipartFile
    -0.49
     lleve
    -0.48
    plotlib
    -0.48
    routeProvider
    -0.48
    IVEREF
    -0.47
     citer
    -0.46
    étation
    -0.46
    POSITIVE LOGITS
     favour
    0.79
     favor
    0.75
     opinion
    0.74
     entirety
    0.72
     spare
    0.70
     faveur
    0.69
    RegressionTest
    0.69
     estimation
    0.66
     youth
    0.65
     quest
    0.64
    Act Density 0.144%

    No Known Activations