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

    Neuronpedia

    INDEX
    Explanations

    instructions related to navigation and skipping sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahir
    -0.19
    ather
    -0.16
    ALLOC
    -0.16
    orks
    -0.15
    .bc
    -0.15
    chos
    -0.15
    idor
    -0.14
    ÅĻÃŃd
    -0.14
    orthand
    -0.14
    nice
    -0.14
    POSITIVE LOGITS
    olson
    0.17
    ocz
    0.17
    aptop
    0.15
    ophy
    0.15
    alon
    0.15
     درÛĮ
    0.14
     bott
    0.14
    duit
    0.14
     regime
    0.14
     dod
    0.14
    Act Density 0.007%

    No Known Activations