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

    Neuronpedia

    INDEX
    Explanations

    words related to simplification and making things easier

    oai_token-act-pair · gpt-3.5-turbo

    words related to simplification and making complex ideas easier to understand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    affer
    -0.71
    wine
    -0.66
     ambassadors
    -0.65
     eminent
    -0.64
    rings
    -0.63
    vine
    -0.62
    kar
    -0.62
    CVE
    -0.61
     tide
    -0.60
    Member
    -0.58
    POSITIVE LOGITS
     simplicity
    0.90
     simpl
    0.88
     simplify
    0.84
    Catalog
    0.82
    fusc
    0.81
     Simpl
    0.79
     simplified
    0.78
    ose
    0.76
     simpler
    0.76
     ABE
    0.74
    Act Density 0.035%

    No Known Activations