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

    Neuronpedia

    INDEX
    Explanations

    tokens or elements that signal significant distinctions or categorizations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eton
    -0.17
    antee
    -0.17
    reeze
    -0.16
     Skill
    -0.15
    .mixin
    -0.15
    pras
    -0.15
    ifter
    -0.15
    fea
    -0.15
    skill
    -0.15
     Hobby
    -0.14
    POSITIVE LOGITS
    CTOR
    0.17
    undry
    0.16
    zano
    0.15
    ONENT
    0.15
     má
    0.15
    arbeit
    0.15
     Laurel
    0.15
     Oliveira
    0.14
    chooser
    0.14
    sdk
    0.14
    Act Density 0.005%

    No Known Activations