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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements related to quantities

    oai_token-act-pair · gpt-3.5-turbo

    sentences and phrases ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.87
     satell
    -0.68
    ascus
    -0.66
    etheless
    -0.63
     lapt
    -0.63
    jriwal
    -0.63
    estic
    -0.61
    Advertisements
    -0.59
    hand
    -0.59
    rid
    -0.58
    POSITIVE LOGITS
     This
    1.04
     They
    1.03
     Instead
    1.01
     Apparently
    1.01
     While
    1.00
     Its
    1.00
     It
    1.00
     Seems
    1.00
     Specifically
    1.00
     Each
    1.00
    Act Density 0.412%

    No Known Activations