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

    Neuronpedia

    INDEX
    Explanations

    phrases related to secret or hidden actions and intentions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stealth or covert actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.84
     Pwr
    -0.82
    rices
    -0.82
    onial
    -0.81
    rises
    -0.78
    minus
    -0.72
    nan
    -0.72
    rification
    -0.71
    oros
    -0.70
    wo
    -0.70
    POSITIVE LOGITS
     sneak
    0.95
    ily
    0.86
     peek
    0.83
    door
    0.76
    atory
    0.71
    hold
    0.71
     sne
    0.71
     glances
    0.69
     Sne
    0.67
    away
    0.66
    Act Density 0.045%

    No Known Activations