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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating advice or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing doubt or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forums
    -0.70
    é¾įå¥ij士
    -0.65
     Principles
    -0.63
    MpServer
    -0.60
     integrity
    -0.60
     affinity
    -0.60
    Graphics
    -0.57
     Altern
    -0.56
     Adin
    -0.56
    igor
    -0.56
    POSITIVE LOGITS
     hear
    0.87
     expect
    0.86
     yourselves
    0.80
     underestimate
    0.79
     need
    0.79
     realise
    0.76
     know
    0.76
    plin
    0.75
    swer
    0.74
     necessarily
    0.73
    Act Density 0.174%

    No Known Activations