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

    Neuronpedia

    INDEX
    Explanations

    misconceptions and misunderstandings related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igs
    -0.20
    (strtolower
    -0.16
    icer
    -0.15
     Schro
    -0.14
    shell
    -0.13
    irting
    -0.13
    å¢ĥ
    -0.13
    otto
    -0.13
     jsonString
    -0.13
    oreach
    -0.13
    POSITIVE LOGITS
    /false
    0.18
    ocrat
    0.16
     about
    0.15
    .localized
    0.15
    .FALSE
    0.14
    cht
    0.14
    arak
    0.14
    以为
    0.14
    fet
    0.14
    eph
    0.14
    Act Density 0.131%

    No Known Activations