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

    Neuronpedia

    INDEX
    Explanations

    dates and events mentioned in a historical or current context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incidents or significant events in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \":
    -0.57
    ':
    -0.57
    ãĤ¨ãĥ«
    -0.56
    "]=>
    -0.56
    vered
    -0.55
    ctive
    -0.55
    å¦
    -0.54
    isable
    -0.52
    isy
    -0.52
    âĶĢâĶĢâĶĢâĶĢ
    -0.50
    POSITIVE LOGITS
     famously
    0.58
     whereas
    0.57
     presumably
    0.57
     unsurprisingly
    0.52
     churn
    0.52
    iferation
    0.51
     supposedly
    0.51
     modeled
    0.49
     gob
    0.49
     soaking
    0.49
    Act Density 1.299%

    No Known Activations