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

    Neuronpedia

    INDEX
    Explanations

    references to news, educational resources, and various forms of media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loub
    -0.17
    /*č↵
    -0.15
    ÃŃÅ¡
    -0.15
    .mx
    -0.15
    chaft
    -0.15
    anmar
    -0.14
    ander
    -0.14
    olist
    -0.14
    subcategory
    -0.14
    etimes
    -0.14
    POSITIVE LOGITS
     acronym
    0.17
     Sith
    0.16
     initials
    0.15
    ез
    0.15
    lopedia
    0.15
    osg
    0.15
    OLOR
    0.15
    vette
    0.14
     god
    0.13
    idge
    0.13
    Act Density 0.175%

    No Known Activations