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

    Neuronpedia

    INDEX
    Explanations

    content related to file paths and directory structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outs
    -0.17
    endi
    -0.15
    compat
    -0.15
    ajs
    -0.13
    yards
    -0.13
    cert
    -0.13
    282
    -0.13
     Figure
    -0.13
    ecs
    -0.13
    ulan
    -0.12
    POSITIVE LOGITS
    çīĻ
    0.15
    ELY
    0.15
    ersive
    0.14
    íĭ°
    0.14
    olars
    0.13
    {}{↵
    0.13
    trainer
    0.13
    loyd
    0.13
    utral
    0.13
    Training
    0.13
    Act Density 0.002%

    No Known Activations