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

    Neuronpedia

    INDEX
    Explanations

    words indicating likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    words expressing probability or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.78
    inventoryQuantity
    -0.66
     Sequ
    -0.62
    assing
    -0.62
     Checking
    -0.61
    quin
    -0.61
     Outer
    -0.60
    DAQ
    -0.59
    assembly
    -0.59
     Shooter
    -0.59
    POSITIVE LOGITS
     be
    1.18
     become
    1.01
     suffice
    0.99
     appear
    0.95
     arrive
    0.92
     come
    0.92
     decide
    0.92
     revert
    0.91
     settle
    0.91
     recognise
    0.91
    Act Density 0.165%

    No Known Activations