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

    Neuronpedia

    INDEX
    Explanations

    HTML list items or links associated with structured content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itchens
    -0.19
    burger
    -0.18
    filer
    -0.15
    erif
    -0.15
     hete
    -0.15
    ngine
    -0.15
    uffer
    -0.14
     Hra
    -0.14
    quare
    -0.14
    avig
    -0.14
    POSITIVE LOGITS
     Rena
    0.15
     Deals
    0.15
    deo
    0.15
    Idle
    0.14
     Donovan
    0.14
    ronym
    0.14
     deals
    0.14
     persu
    0.14
    933
    0.14
    coh
    0.13
    Act Density 0.013%

    No Known Activations