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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interior locations or states of being

    oai_token-act-pair · gpt-3.5-turbo

    sentences or clauses that convey finality or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.78
    apper
    -0.76
    ividual
    -0.75
    omics
    -0.74
     boutique
    -0.73
    itional
    -0.71
    iler
    -0.70
    affer
    -0.69
    cki
    -0.69
    eatured
    -0.68
    POSITIVE LOGITS
     Slowly
    1.07
     Luckily
    1.06
     Dumbledore
    1.05
     Jaune
    1.05
     Thankfully
    1.05
     Something
    1.03
     Besides
    1.03
     Fortunately
    1.01
     Suddenly
    0.99
     Afterwards
    0.99
    Act Density 0.261%

    No Known Activations