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

    Neuronpedia

    INDEX
    Explanations

    terms related to positivity and optimism

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESH
    -0.74
     Skies
    -0.73
    ãģ®å®
    -0.71
     Brilliant
    -0.69
    åĮ
    -0.68
     Mellon
    -0.67
     Maw
    -0.65
    æĸ¹
    -0.64
     Flavoring
    -0.64
    loo
    -0.63
    POSITIVE LOGITS
     pos
    1.27
    itivity
    1.01
    idon
    0.96
    pos
    0.96
    sembly
    0.95
    itional
    0.89
    fet
    0.88
     posit
    0.87
    itory
    0.84
    nick
    0.83
    Act Density 0.011%

    No Known Activations