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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive adjectives refering to people

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nob
    -0.65
    jar
    -0.64
    gar
    -0.60
     UCHIJ
    -0.60
    Mand
    -0.58
    iting
    -0.57
    Ty
    -0.56
     Sidd
    -0.56
    onda
    -0.55
    let
    -0.55
    POSITIVE LOGITS
    xus
    0.82
    urally
    0.70
     differently
    0.66
    ãĤ¦
    0.66
    ACTED
    0.65
     behav
    0.65
    ãĤ¼ãĤ¦ãĤ¹
    0.64
    ²¾
    0.64
    EMS
    0.64
    Reviewer
    0.63
    Act Density 0.605%

    No Known Activations