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

    Neuronpedia

    INDEX
    Explanations

    phrases describing newly acquired knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    expressions of acquired knowledge or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.74
    oided
    -0.71
     throats
    -0.65
     pers
    -0.64
    idity
    -0.64
    adies
    -0.62
    ankind
    -0.62
    ataka
    -0.61
    yip
    -0.58
    vell
    -0.58
    POSITIVE LOGITS
    llor
    0.90
    Lear
    0.81
    ilage
    0.79
    lyn
    0.77
    çīĪ
    0.75
    æ©
    0.75
     firsthand
    0.75
    æĥ
    0.73
    CLASSIFIED
    0.73
    learn
    0.72
    Act Density 0.028%

    No Known Activations