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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "preserve" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "presidential" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bed
    -0.90
    nered
    -0.85
    bing
    -0.84
    ly
    -0.78
    bers
    -0.77
    ress
    -0.72
    cles
    -0.72
    icide
    -0.71
    TAIN
    -0.70
    ing
    -0.69
    POSITIVE LOGITS
    acht
    0.82
    agram
    0.78
    alez
    0.77
    ateg
    0.74
    wow
    0.73
    acc
    0.73
    hemat
    0.71
    odic
    0.70
    uten
    0.70
    andise
    0.69
    Act Density 0.111%

    No Known Activations