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

    Neuronpedia

    INDEX
    Explanations

    personal opinions or assessments

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related expressions of personal opinion or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adobe
    -0.76
    needed
    -0.70
    itud
    -0.68
    س
    -0.68
     Lauder
    -0.67
    ihil
    -0.66
    wav
    -0.65
    ensis
    -0.65
    POST
    -0.64
    $$
    -0.64
    POSITIVE LOGITS
    stery
    1.33
    anmar
    1.21
     goal
    1.18
     apologies
    1.16
     condolences
    1.14
     wife
    1.13
     colleague
    1.13
     favorite
    1.10
     favourite
    1.10
     intention
    1.09
    Act Density 0.093%

    No Known Activations