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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and terms related to familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĻ
    -0.17
    /fonts
    -0.15
    implicit
    -0.15
    ocz
    -0.14
    urette
    -0.14
    bose
    -0.14
    Tube
    -0.14
    ouz
    -0.14
    opsis
    -0.14
    oulos
    -0.14
    POSITIVE LOGITS
    axon
    0.15
     tròn
    0.15
    omanip
    0.14
     Interpreter
    0.14
     fer
    0.14
    -unstyled
    0.14
    iminal
    0.14
    367
    0.14
     verg
    0.13
     Nas
    0.13
    Act Density 0.109%

    No Known Activations