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

    Neuronpedia

    INDEX
    Explanations

    phrases related to structured systems or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to various schemes or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĹ
    -0.65
    Flo
    -0.64
    inas
    -0.64
     Clover
    -0.63
    azines
    -0.61
     Hug
    -0.59
     Hond
    -0.59
    Rum
    -0.59
    Nob
    -0.59
     Qiao
    -0.58
    POSITIVE LOGITS
     scheme
    1.07
     schemes
    1.06
     devised
    0.87
    etary
    0.85
    ĸļ
    0.84
    eers
    0.80
    ulence
    0.79
    eering
    0.77
    matic
    0.74
    matically
    0.72
    Act Density 0.013%

    No Known Activations