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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    statements about intent or purpose in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.79
    piracy
    -0.74
    arat
    -0.71
    sequently
    -0.68
     deserve
    -0.64
    sequent
    -0.63
    ynski
    -0.63
     Dise
    -0.62
    iversary
    -0.61
    wake
    -0.61
    POSITIVE LOGITS
     indistinguishable
    0.91
     predomin
    0.69
     pitted
    0.69
    emin
    0.68
    stood
    0.67
     conspicuous
    0.67
    omorphic
    0.66
     referred
    0.65
    omorph
    0.64
     evident
    0.64
    Act Density 0.669%

    No Known Activations