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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "coming"

    oai_token-act-pair · gpt-3.5-turbo

    references to future time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mel
    -0.85
    cius
    -0.84
    olor
    -0.82
    hemy
    -0.80
    ording
    -0.79
    eva
    -0.75
    paio
    -0.75
    vg
    -0.75
    lua
    -0.74
    inet
    -0.74
    POSITIVE LOGITS
     generations
    1.03
     weeks
    0.99
     days
    0.94
     months
    0.88
     incarnation
    0.86
     week
    0.84
     installment
    0.84
     attractions
    0.83
     generation
    0.83
     iteration
    0.80
    Act Density 0.022%

    No Known Activations