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

    Neuronpedia

    INDEX
    Explanations

    constructs related to institutional references or designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wen
    -0.15
    akan
    -0.15
    pler
    -0.15
    wap
    -0.15
    apot
    -0.14
    yw
    -0.14
    awk
    -0.14
    898
    -0.14
    anke
    -0.14
    andan
    -0.13
    POSITIVE LOGITS
    urgical
    0.15
     Benghazi
    0.14
    instein
    0.14
    cls
    0.14
    arf
    0.14
    .sig
    0.14
    ultan
    0.14
    rien
    0.14
     fret
    0.13
    625
    0.13
    Act Density 0.012%

    No Known Activations