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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "in" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases indicating compliance or alignment with guidelines or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.84
    cia
    -0.72
     greets
    -0.70
    DragonMagazine
    -0.69
     interacts
    -0.69
     induces
    -0.64
     haircut
    -0.63
     introduces
    -0.63
     reacts
    -0.63
    laughs
    -0.62
    POSITIVE LOGITS
    escap
    1.03
    versely
    0.94
     essence
    0.91
    avering
    0.82
     fact
    0.81
    cluded
    0.80
    herent
    0.76
    clusive
    0.75
    arg
    0.75
    alle
    0.74
    Act Density 0.237%

    No Known Activations