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

    Neuronpedia

    INDEX
    Explanations

    statements asserting or challenging claims

    oai_token-act-pair · gpt-3.5-turbo

    references to assertions or statements of belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srf
    -0.95
    cffffcc
    -0.87
     Watching
    -0.80
     arrang
    -0.78
     electing
    -0.73
     simul
    -0.73
     newcom
    -0.72
    etheless
    -0.71
     stocking
    -0.71
     destro
    -0.65
    POSITIVE LOGITS
     claims
    1.10
    Claim
    1.03
     claim
    1.00
    ifications
    0.83
    ylum
    0.81
     Claim
    0.80
    BILITY
    0.80
    ulent
    0.79
     Cheong
    0.79
    oux
    0.79
    Act Density 0.011%

    No Known Activations