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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a positive evaluation or opinion

    oai_token-act-pair · gpt-3.5-turbo

    positive adjectives expressing high quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etus
    -0.67
    ournal
    -0.65
    ilings
    -0.65
    ibliography
    -0.65
    ravings
    -0.64
    earance
    -0.64
    uthor
    -0.63
    idas
    -0.62
    uke
    -0.61
    pend
    -0.61
    POSITIVE LOGITS
     enough
    1.02
    ãĤ´
    0.78
     hubs
    0.75
    nell
    0.75
    aneously
    0.72
     nonetheless
    0.66
     XD
    0.66
     additions
    0.65
     surpr
    0.65
     Dahl
    0.64
    Act Density 0.207%

    No Known Activations