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

    Neuronpedia

    INDEX
    Explanations

    references to a television network or channel (ND TV)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the acronym "ND" and related items, indicating a focus on news topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pell
    -0.91
    acters
    -0.90
    hold
    -0.83
    acter
    -0.79
    ============
    -0.78
    ========
    -0.77
    rosse
    -0.75
    ================
    -0.74
    cent
    -0.74
    chwitz
    -0.70
    POSITIVE LOGITS
    ND
    1.06
    epend
    0.91
     ND
    0.89
    ependent
    0.84
    ENSE
    0.82
    LR
    0.80
    IFF
    0.76
    NF
    0.74
    irect
    0.74
    IA
    0.74
    Act Density 0.011%

    No Known Activations