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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating qualities or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upa
    -0.16
     abstraction
    -0.16
    <?,
    -0.14
    824
    -0.14
    aid
    -0.14
    \Lib
    -0.14
    alue
    -0.14
    lush
    -0.13
    ä¹ĭ
    -0.13
    oyer
    -0.13
    POSITIVE LOGITS
    л
    0.16
    _COMPAT
    0.14
    incinn
    0.14
    izza
    0.14
    ricks
    0.14
    anko
    0.14
    urrenc
    0.13
    éal
    0.13
    ippo
    0.13
    IRC
    0.13
    Act Density 0.217%

    No Known Activations