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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    various forms of punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.67
     robber
    -0.66
     overlooked
    -0.65
     tremend
    -0.65
     namesake
    -0.65
    nen
    -0.65
     slightest
    -0.64
    ikuman
    -0.64
     metic
    -0.64
     undet
    -0.63
    POSITIVE LOGITS
     Additionally
    1.22
     Together
    1.09
     However
    1.08
     They
    1.07
     These
    1.06
     Their
    1.06
     Both
    1.06
     Also
    1.03
     Each
    1.01
     Eventually
    0.99
    Act Density 0.900%

    No Known Activations