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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to positive experiences and emotions

    oai_token-act-pair · gpt-3.5-turbo

    words related to excitement and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respecting
    -0.72
    sup
    -0.69
    ©¶æ
    -0.68
    ariat
    -0.67
    ohn
    -0.66
    sama
    -0.64
    gemony
    -0.63
    idelines
    -0.63
    avia
    -0.62
    christ
    -0.62
    POSITIVE LOGITS
    ly
    0.92
     Flavoring
    0.88
    \\\\\\\\
    0.85
     surprises
    0.75
    iliar
    0.75
    nels
    0.73
     ride
    0.71
    nell
    0.71
     experiences
    0.70
    glers
    0.70
    Act Density 0.132%

    No Known Activations