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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olon
    -0.16
    OLON
    -0.15
    anke
    -0.14
    亲
    -0.14
    åī¯
    -0.14
    éŀ
    -0.14
    ekli
    -0.14
    deen
    -0.14
    OLER
    -0.14
    verbosity
    -0.13
    POSITIVE LOGITS
    erties
    0.17
     Ree
    0.16
    iter
    0.15
    znik
    0.15
     Gall
    0.15
    caa
    0.15
    gang
    0.14
    ernen
    0.14
    eras
    0.14
    acio
    0.14
    Act Density 0.000%

    No Known Activations