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

    Neuronpedia

    INDEX
    Explanations

    instances of communication methods and language use, especially in educational or explanatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiener
    -0.17
    rig
    -0.16
    jis
    -0.16
    imited
    -0.15
    ridor
    -0.14
    opsis
    -0.14
    èĦij
    -0.14
    uster
    -0.14
    .central
    -0.14
    ãģĹãģĭ
    -0.14
    POSITIVE LOGITS
    857
    0.16
    ariat
    0.15
    plates
    0.15
    ãĥªãĤ«
    0.15
    ildren
    0.14
    ÑĢаÑħ
    0.14
    Explicit
    0.14
    explicit
    0.14
    å¨
    0.14
    601
    0.14
    Act Density 0.306%

    No Known Activations