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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "still" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "still" indicating continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.70
    stice
    -0.67
    ongyang
    -0.65
    alties
    -0.65
    assi
    -0.63
    ospace
    -0.63
    osion
    -0.61
    iHUD
    -0.60
    ¶ħ
    -0.60
    odan
    -0.60
    POSITIVE LOGITS
    birth
    1.13
    born
    1.11
     reeling
    0.99
     alive
    0.95
     intact
    0.92
     figuring
    0.90
     undecided
    0.88
     recovering
    0.80
     evolving
    0.79
     clinging
    0.78
    Act Density 0.069%

    No Known Activations