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

    Neuronpedia

    INDEX
    Explanations

    names of authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.18
    nicas
    -0.16
    orz
    -0.16
    alu
    -0.16
     Hä
    -0.16
    ught
    -0.15
    uais
    -0.15
    osti
    -0.15
    onas
    -0.14
    hte
    -0.14
    POSITIVE LOGITS
    acker
    0.14
    ember
    0.14
    ÏĢοÏħ
    0.14
    ollow
    0.14
    ÏĢοÏį
    0.14
    atinum
    0.14
    SKI
    0.14
    ushort
    0.13
    åŃĿ
    0.13
    SHA
    0.13
    Act Density 0.019%

    No Known Activations