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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is speaking out, expressing opinions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of speaking out or expressing opinions on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.83
    atomic
    -0.73
     Jackets
    -0.70
    ipment
    -0.67
     Landing
    -0.67
    Gs
    -0.63
    jiang
    -0.63
    Rocket
    -0.62
     refres
    -0.61
    plet
    -0.61
    POSITIVE LOGITS
     loudly
    1.12
     against
    1.11
     louder
    1.11
     forcefully
    1.10
     loud
    0.99
     anonymously
    0.98
     publicly
    0.94
    against
    0.91
     boldly
    0.88
     angrily
    0.86
    Act Density 0.065%

    No Known Activations