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

    Neuronpedia

    INDEX
    Explanations

    the preposition "to"

    oai_token-act-pair · gpt-3.5-turbo

    empty or placeholder sections within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulner
    -0.66
     Seym
    -0.63
     Niet
    -0.61
     campaigned
    -0.59
     tooth
    -0.54
     mortg
    -0.53
     Azerb
    -0.53
     outing
    -0.51
     pockets
    -0.51
     millenn
    -0.51
    POSITIVE LOGITS
    ggles
    1.15
    wered
    0.99
    ilet
    0.94
    pload
    0.93
    pless
    0.85
    othy
    0.85
     enable
    0.85
     stabilize
    0.85
    dos
    0.84
    asted
    0.84
    Act Density 0.047%

    No Known Activations