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

    Neuronpedia

    INDEX
    Explanations

    terms related to searching and investigations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to search activities or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivari
    -0.82
    Production
    -0.79
     Leilan
    -0.71
    minecraft
    -0.65
    EStreamFrame
    -0.63
    Earn
    -0.63
    Torrent
    -0.63
     imitation
    -0.62
    nect
    -0.61
    Downloadha
    -0.61
    POSITIVE LOGITS
     engines
    0.88
     warrant
    0.82
    prising
    0.75
     warrants
    0.75
    suits
    0.75
     Warrant
    0.75
     engine
    0.75
    lights
    0.73
    suit
    0.71
    able
    0.70
    Act Density 0.023%

    No Known Activations