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

    Neuronpedia

    INDEX
    Explanations

    phrases that compare or contrast similarities and differences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the notion of political context or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shalt
    -0.74
    interrupted
    -0.73
    quished
    -0.70
    hett
    -0.68
    IAN
    -0.67
     Collider
    -0.67
    lost
    -0.64
    aunder
    -0.63
    itten
    -0.62
    istani
    -0.62
    POSITIVE LOGITS
     nature
    1.34
     origin
    1.10
     disguise
    1.10
     appearance
    1.07
     tone
    1.03
     principle
    1.02
     scope
    1.01
     comparison
    0.97
     terms
    0.97
     stature
    0.97
    Act Density 0.143%

    No Known Activations