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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to software installation and configuration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" within technical instructions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ°
    -0.91
    jah
    -0.80
    Bey
    -0.70
    TextColor
    -0.69
    اØ
    -0.69
    soDeliveryDate
    -0.69
    perse
    -0.66
    Tan
    -0.66
    ÙĬ
    -0.66
    BILL
    -0.66
    POSITIVE LOGITS
     behalf
    1.31
    coming
    0.98
     occasion
    0.98
    sets
    0.94
    erous
    0.93
     startup
    0.89
     Github
    0.88
    eworld
    0.88
    slaught
    0.87
    shore
    0.85
    Act Density 0.187%

    No Known Activations