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

    Neuronpedia

    INDEX
    Explanations

    natural elements and their uses in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Salt
    -0.20
     salt
    -0.20
    salt
    -0.19
    Salt
    -0.18
    onaut
    -0.15
    ppelin
    -0.15
    _salt
    -0.14
    ambi
    -0.14
    ptron
    -0.14
    \Dependency
    -0.14
    POSITIVE LOGITS
     hier
    0.20
     fri
    0.19
    ervas
    0.19
     Hier
    0.18
     unt
    0.18
    arena
    0.17
     hid
    0.17
    Hier
    0.17
     arena
    0.17
     arada
    0.17
    Act Density 0.037%

    No Known Activations