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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance and entertainment abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alarm
    -0.20
     alarms
    -0.18
     Alarm
    -0.17
    710
    -0.16
    pit
    -0.16
     Stall
    -0.16
    ellt
    -0.15
     pit
    -0.15
     GPS
    -0.15
    alarm
    -0.15
    POSITIVE LOGITS
     magician
    0.26
     magic
    0.24
     card
    0.24
    magic
    0.21
     Magic
    0.21
     cards
    0.20
    Cards
    0.20
    .magic
    0.20
    _magic
    0.20
     mag
    0.19
    Act Density 0.014%

    No Known Activations