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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to technology products

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the pronoun "It" to describe various features or qualities of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dding
    -0.65
    anton
    -0.60
     persuasion
    -0.60
    hips
    -0.59
    dden
    -0.56
     Corpus
    -0.56
    Ĥ¬
    -0.55
    course
    -0.55
     Rebellion
    -0.55
     Westminster
    -0.54
    POSITIVE LOGITS
    unes
    1.14
    alian
    1.11
    'll
    1.09
     contains
    1.03
    chy
    1.02
    self
    1.02
     consists
    1.00
     seems
    1.00
    's
    0.99
     incorporates
    0.97
    Act Density 0.288%

    No Known Activations