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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    an end-of-text signal or the conclusion of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.74
     derog
    -0.69
     misunder
    -0.68
     reperto
    -0.67
     prest
    -0.65
     destro
    -0.65
    accompan
    -0.64
    forth
    -0.64
    bet
    -0.64
    ucci
    -0.62
    POSITIVE LOGITS
     course
    0.84
     sorts
    0.76
     Horror
    0.69
     Tradable
    0.68
     SHARES
    0.66
    course
    0.64
     Course
    0.63
    UTERS
    0.63
     Psy
    0.61
    icial
    0.61
    Act Density 0.039%

    No Known Activations