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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or suspense

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases or indicators that suggest pausing or waiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.75
    ortium
    -0.69
    reb
    -0.66
    iverpool
    -0.66
    ãĤº
    -0.65
    insula
    -0.62
    uded
    -0.60
     Scotia
    -0.59
     Ob
    -0.58
    ighter
    -0.58
    POSITIVE LOGITS
     till
    1.01
     patiently
    1.00
     til
    0.91
     until
    0.89
    listed
    0.89
    resses
    0.88
    eful
    0.86
    rose
    0.85
    gap
    0.85
    wait
    0.82
    Act Density 0.030%

    No Known Activations