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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tracking or monitoring

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to monitoring or keeping record of various items or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.70
    vette
    -0.60
    Reply
    -0.58
     pand
    -0.58
    osi
    -0.56
     Synd
    -0.56
     Debor
    -0.56
    lication
    -0.55
    iren
    -0.55
    Prime
    -0.55
    POSITIVE LOGITS
    suit
    0.96
    pad
    0.89
    suits
    0.89
     Tracks
    0.85
     track
    0.84
    tracks
    0.83
     tracks
    0.82
    track
    0.82
    record
    0.81
    race
    0.81
    Act Density 0.019%

    No Known Activations