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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing things or people

    oai_token-act-pair · gpt-3.5-turbo

    the word "wonderful" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.90
    gemony
    -0.86
    olate
    -0.74
    phrine
    -0.73
    opers
    -0.72
    eter
    -0.71
    avis
    -0.71
    pper
    -0.71
    eters
    -0.67
    bryce
    -0.67
    POSITIVE LOGITS
     Samar
    0.76
     Asgard
    0.76
    astically
    0.75
     opportunity
    0.75
    NESS
    0.74
     scenery
    0.72
    owship
    0.71
     Wonderful
    0.70
     Aunt
    0.70
     Lakes
    0.69
    Act Density 0.033%

    No Known Activations