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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or development

    oai_token-act-pair · gpt-3.5-turbo

    recurring instances of the word "the" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hari
    -0.68
     refers
    -0.64
     belonged
    -0.64
    !!!!
    -0.63
    !!
    -0.62
     consists
    -0.62
     consisted
    -0.62
    anova
    -0.61
    pelled
    -0.61
     because
    -0.60
    POSITIVE LOGITS
     latter
    1.19
     slightest
    1.13
     aforementioned
    1.08
     ensuing
    1.04
     remainder
    1.03
     entirety
    1.03
     same
    0.99
     vast
    0.98
     confines
    0.97
     proverbial
    0.96
    Act Density 0.997%

    No Known Activations