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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sustaining or support

    oai_token-act-pair · gpt-3.5-turbo

    references to sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blossom
    -0.79
    ramid
    -0.77
    Ĭ±
    -0.74
    onym
    -0.72
    uni
    -0.69
     Jere
    -0.67
     Mehran
    -0.66
    ography
    -0.66
     plaza
    -0.65
    ology
    -0.65
    POSITIVE LOGITS
    ably
    1.12
    mental
    0.97
     sustained
    0.89
    ently
    0.85
    ive
    0.80
     sustain
    0.79
    edly
    0.79
    aign
    0.78
    robe
    0.78
    rition
    0.77
    Act Density 0.044%

    No Known Activations