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

    Neuronpedia

    INDEX
    Explanations

    title-like phrases or headings within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acz
    -0.15
    apter
    -0.15
    iene
    -0.15
    riot
    -0.14
    -ng
    -0.14
    805
    -0.14
    kowski
    -0.14
    hya
    -0.14
    704
    -0.13
    ãģ¾ãģŁ
    -0.13
    POSITIVE LOGITS
    ãģĸ
    0.15
    annon
    0.14
     Mit
    0.14
    roc
    0.14
    rise
    0.13
    RootElement
    0.13
    çł
    0.13
    /MPL
    0.13
    todo
    0.13
    inkel
    0.13
    Act Density 0.052%

    No Known Activations