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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things unexpectedly appearing or being discovered

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "pop up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arine
    -0.75
     CLSID
    -0.71
    apy
    -0.71
    sis
    -0.70
    robe
    -0.70
    mens
    -0.68
    ct
    -0.68
    avering
    -0.68
    ape
    -0.66
    ided
    -0.66
    POSITIVE LOGITS
     spontaneously
    1.04
     everywhere
    0.89
     prominently
    0.83
     anywhere
    0.77
     nowhere
    0.75
    river
    0.75
     mysteriously
    0.71
     banners
    0.71
     begging
    0.70
     elsewhere
    0.70
    Act Density 0.094%

    No Known Activations