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

    Neuronpedia

    INDEX
    Explanations

    relationships between variables and conditional effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     %+
    -0.15
    cket
    -0.14
    dek
    -0.14
    éĹ²
    -0.14
    à¥įयम
    -0.14
    åįĶ
    -0.13
    ots
    -0.13
    ìĿ¼ìĹIJ
    -0.13
    bou
    -0.13
     Goat
    -0.13
    POSITIVE LOGITS
     Hun
    0.15
    ourcem
    0.14
    embed
    0.14
     multin
    0.14
    452
    0.14
    ivities
    0.14
     uniforms
    0.14
    ifr
    0.14
    Keyboard
    0.14
    tee
    0.13
    Act Density 0.645%

    No Known Activations