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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or continuity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize repetition or returning to a previous point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eways
    -0.70
    adena
    -0.69
    ocene
    -0.68
    ottage
    -0.67
    izons
    -0.67
    oslav
    -0.64
    76561
    -0.64
    oming
    -0.63
    oreal
    -0.61
    л
    -0.59
    POSITIVE LOGITS
    nces
    0.76
     reiterate
    0.73
     illustrating
    0.72
     proving
    0.71
     echoing
    0.68
     quoting
    0.67
     revolving
    0.66
    tical
    0.65
     emphas
    0.65
     demonstrating
    0.65
    Act Density 0.042%

    No Known Activations