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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of things that are new or recently made

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fresh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rael
    -0.76
    owered
    -0.70
     Donation
    -0.69
    oried
    -0.66
    idget
    -0.66
    auga
    -0.64
    Ĥİ
    -0.63
    king
    -0.63
    respect
    -0.63
    iquid
    -0.63
    POSITIVE LOGITS
    ness
    1.13
    lish
    0.96
    foundland
    0.81
     fresh
    0.78
     scratch
    0.77
    lishes
    0.76
    bie
    0.75
    Fresh
    0.74
    lings
    0.73
    lic
    0.70
    Act Density 0.016%

    No Known Activations