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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional reassurance and self-assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sobie
    -0.17
     شر
    -0.15
     Celt
    -0.14
    à¥ģश
    -0.14
    tract
    -0.14
     abstract
    -0.14
    shelf
    -0.14
    784
    -0.13
    anela
    -0.13
     sobÄĽ
    -0.13
    POSITIVE LOGITS
    572
    0.15
    _regularizer
    0.15
    upd
    0.15
    stor
    0.15
    /xhtml
    0.15
    iode
    0.14
    inder
    0.14
    .qt
    0.14
    pcl
    0.14
    attery
    0.14
    Act Density 0.275%

    No Known Activations