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

    Neuronpedia

    INDEX
    Explanations

    phrases related to keeping something alive or in a particular state

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to maintaining and preserving things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haps
    -0.78
    ĪĴ
    -0.74
     DRAG
    -0.74
     Result
    -0.65
    interstitial
    -0.65
    çīĪ
    -0.64
    lication
    -0.63
    ramid
    -0.63
    tery
    -0.62
     profiling
    -0.60
    POSITIVE LOGITS
     intact
    0.88
     indefinitely
    0.87
    clud
    0.86
     afloat
    0.78
     steady
    0.71
     uninterrupted
    0.71
     alive
    0.67
     sterile
    0.66
     entertained
    0.66
    enged
    0.65
    Act Density 0.193%

    No Known Activations