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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing complexity or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to complex situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vation
    -0.83
    uin
    -0.82
    emp
    -0.81
    eele
    -0.76
    entin
    -0.75
    vertising
    -0.74
    inth
    -0.73
    ablishment
    -0.73
    apons
    -0.72
    sburg
    -0.70
    POSITIVE LOGITS
     complicated
    0.87
     complicate
    0.86
     convoluted
    0.84
     matters
    0.77
     baff
    0.71
     solved
    0.70
     unnecess
    0.69
     nuances
    0.69
     calculus
    0.69
     Mysteries
    0.68
    Act Density 0.058%

    No Known Activations