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

    Neuronpedia

    INDEX
    Explanations

    words related to solving or addressing issues

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to correction or fixing problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.65
    ortment
    -0.64
     headlined
    -0.63
     accompanied
    -0.63
    ever
    -0.63
     placed
    -0.61
     invitation
    -0.61
    luster
    -0.60
    umer
    -0.60
    pmwiki
    -0.60
    POSITIVE LOGITS
    balance
    0.79
    iencies
    0.75
     grievances
    0.72
    ysis
    0.72
    igate
    0.71
    ilitating
    0.71
     them
    0.69
    uate
    0.67
    ulate
    0.67
     their
    0.65
    Act Density 0.118%

    No Known Activations