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

    Neuronpedia

    INDEX
    Explanations

    connections to names and references within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĿ
    -0.17
    itung
    -0.16
    criptive
    -0.16
    licht
    -0.15
    amilia
    -0.14
    ÏĦÏģα
    -0.14
    loff
    -0.14
    ozor
    -0.14
    umpy
    -0.14
    ourke
    -0.14
    POSITIVE LOGITS
    /extensions
    0.16
     Matth
    0.16
    ylko
    0.15
    rophe
    0.15
     impression
    0.14
     Gat
    0.14
     unw
    0.14
    ÙĦاÙĨ
    0.14
     coincidence
    0.13
    å¥Ķ
    0.13
    Act Density 0.108%

    No Known Activations