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

    Neuronpedia

    INDEX
    Explanations

    references to fitting or appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dising
    -0.52
    __*/
    -0.49
     Bulletin
    -0.47
    mobileqq
    -0.46
     Interrupt
    -0.46
     bulletins
    -0.45
    manufactured
    -0.45
     Institution
    -0.45
    zon
    -0.44
     Joint
    -0.44
    POSITIVE LOGITS
     context
    0.74
     Kontext
    0.66
     contexte
    0.66
     mourut
    0.65
     contexts
    0.65
     death
    0.62
     fit
    0.61
    Death
    0.59
     контек
    0.57
     Death
    0.57
    Act Density 0.218%

    No Known Activations