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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating future plans or events

    oai_token-act-pair · gpt-3.5-turbo

    references to planning and anticipation of future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ordinary
    -0.82
     coerc
    -0.79
     dehuman
    -0.77
     misrepresent
    -0.76
     discern
    -0.74
     submerged
    -0.73
     eroded
    -0.71
     incorrectly
    -0.71
     imperson
    -0.71
     displaced
    -0.70
    POSITIVE LOGITS
    Tickets
    1.04
     Hopefully
    1.01
    Anyway
    1.00
     Amen
    1.00
     THANK
    0.99
    ————————————————
    0.98
     ðŁĺ
    0.98
     ðŁĻĤ
    0.97
    ðŁĺ
    0.97
    Thank
    0.97
    Act Density 0.660%

    No Known Activations