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

    Neuronpedia

    INDEX
    Explanations

    specific information related to dates and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to coaching and instruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.50
    trump
    -0.49
    greg
    -0.48
    ]).
    -0.48
    issance
    -0.47
     Beir
    -0.47
    ciation
    -0.47
    jiang
    -0.45
    çĶ°
    -0.44
    etheless
    -0.44
    POSITIVE LOGITS
     knowing
    0.45
     stale
    0.43
     expecting
    0.43
     weaker
    0.43
     bounce
    0.40
    ecause
    0.39
     weak
    0.39
     crappy
    0.39
     because
    0.39
     liter
    0.38
    Act Density 4.391%

    No Known Activations