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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries seeking explanations or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omnia
    -0.15
    isen
    -0.14
    ÙģتÙĩ
    -0.14
    brit
    -0.14
    dess
    -0.14
    rung
    -0.14
    gett
    -0.14
    ãĥ³ãĥķ
    -0.13
    ẹ
    -0.13
    ạ
    -0.13
    POSITIVE LOGITS
     exactly
    0.35
     Exactly
    0.27
    Exactly
    0.24
     genau
    0.22
     precisely
    0.20
     does
    0.18
     exact
    0.18
     Does
    0.16
    _does
    0.16
     pÅĻesnÄĽ
    0.15
    Act Density 0.052%

    No Known Activations