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

    Neuronpedia

    INDEX
    Explanations

    occurrences of historical dates or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctp
    -0.17
    HIR
    -0.15
    zych
    -0.15
    ihn
    -0.14
     Watson
    -0.14
     reass
    -0.13
     tolerance
    -0.13
    uzey
    -0.13
     Toll
    -0.13
    ego
    -0.13
    POSITIVE LOGITS
    eno
    0.14
    boxed
    0.14
    elight
    0.14
    iyon
    0.14
    ibel
    0.14
    oucher
    0.14
    ftware
    0.14
    trand
    0.13
     prick
    0.13
     Kimber
    0.13
    Act Density 0.007%

    No Known Activations