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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe something new or recently made

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being new or revitalized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rael
    -0.77
     Donation
    -0.70
    idget
    -0.68
    oried
    -0.66
    ylum
    -0.65
    oris
    -0.65
    guided
    -0.64
    adian
    -0.64
    auga
    -0.64
    Ĥİ
    -0.64
    POSITIVE LOGITS
    ness
    1.18
    lish
    0.91
    foundland
    0.81
     fresh
    0.77
    lings
    0.76
     scratch
    0.75
     breeze
    0.73
     batch
    0.72
    bie
    0.72
    water
    0.71
    Act Density 0.025%

    No Known Activations