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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Heidelberg" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marshall
    -0.18
    hoo
    -0.17
    marshall
    -0.16
    ordo
    -0.16
     Christmas
    -0.15
    Christmas
    -0.15
    že
    -0.14
    δή
    -0.14
     Mage
    -0.14
    ¢
    -0.14
    POSITIVE LOGITS
    723
    0.17
    ahi
    0.15
    anni
    0.15
    anke
    0.15
    pga
    0.14
    bine
    0.14
    urette
    0.14
    bett
    0.13
    ulan
    0.13
    ADER
    0.13
    Act Density 0.305%

    No Known Activations