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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and terms within a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fav
    -0.15
    оÑĤе
    -0.15
    alan
    -0.14
    ines
    -0.14
    ulen
    -0.14
     darm
    -0.14
     Lear
    -0.14
    ç§ĺ
    -0.14
    ulus
    -0.14
    ukes
    -0.14
    POSITIVE LOGITS
    ree
    0.16
    PRS
    0.15
     Pathfinder
    0.15
    ève
    0.15
    athan
    0.15
     京
    0.14
    eree
    0.14
     smrt
    0.14
    _compiler
    0.14
    STA
    0.14
    Act Density 0.039%

    No Known Activations