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

    Neuronpedia

    INDEX
    Explanations

    expressions related to presence or existence

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of being present or nearby

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.77
    oÄŁ
    -0.70
    ĪĴ
    -0.70
    ãĤº
    -0.68
    ELS
    -0.68
    elf
    -0.64
    Ts
    -0.62
    elman
    -0.62
    eln
    -0.62
    aries
    -0.62
    POSITIVE LOGITS
     town
    0.90
     corners
    0.81
     forever
    0.80
     awhile
    0.78
    abouts
    0.77
     longer
    0.71
     here
    0.69
     anymore
    0.68
     :-)
    0.66
     :)
    0.64
    Act Density 0.035%

    No Known Activations