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

    Neuronpedia

    INDEX
    Explanations

    future time frames

    oai_token-act-pair · gpt-3.5-turbo

    references to time frames or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mel
    -0.99
    olor
    -0.87
    vg
    -0.86
    hemy
    -0.85
    cius
    -0.84
    tops
    -0.82
    irit
    -0.79
    lua
    -0.79
    itars
    -0.78
    fur
    -0.78
    POSITIVE LOGITS
     attractions
    0.91
     generations
    0.91
     weeks
    0.90
     days
    0.81
     week
    0.79
     installment
    0.79
     arrival
    0.76
     round
    0.75
     incarnation
    0.74
     months
    0.73
    Act Density 0.022%

    No Known Activations