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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to knowing or information

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.68
    ceive
    -0.62
    advertising
    -0.62
     representing
    -0.62
    thood
    -0.61
    pload
    -0.61
    ccoli
    -0.61
    entimes
    -0.61
    usb
    -0.60
     owing
    -0.60
    POSITIVE LOGITS
     slightest
    1.13
    ses
    1.12
     possibility
    1.11
     same
    1.10
     latest
    1.10
     entire
    1.10
     entirety
    1.09
     difference
    1.09
     smallest
    1.05
     beginnings
    1.04
    Act Density 0.470%

    No Known Activations