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

    Neuronpedia

    INDEX
    Explanations

    sequences involving an initial action and a subsequent action

    oai_token-act-pair · gpt-3.5-turbo

    sequences that indicate a progression of actions or steps taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.70
    than
    -0.66
    ction
    -0.62
    venture
    -0.62
    kson
    -0.61
     Benson
    -0.61
    toe
    -0.60
    str
    -0.60
    md
    -0.60
    Vision
    -0.60
    POSITIVE LOGITS
     proceeded
    1.06
     secondly
    0.87
     proceed
    0.87
     succumb
    0.84
     promptly
    0.79
     conclud
    0.79
     proceeds
    0.78
     abruptly
    0.76
     disappear
    0.75
     disappears
    0.74
    Act Density 0.050%

    No Known Activations