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

    Neuronpedia

    INDEX
    Explanations

    words related to feelings of extreme disgust or anger

    oai_token-act-pair · gpt-3.5-turbo

    variants of the word "disgust" or related words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saras
    -0.64
     convergence
    -0.61
     Palest
    -0.61
    Äĩ
    -0.61
     astronomers
    -0.61
     hypers
    -0.60
    ãĤ´ãĥ³
    -0.59
     HDL
    -0.59
     recommendation
    -0.58
     Skydragon
    -0.58
    POSITIVE LOGITS
    ption
    0.99
    owship
    0.87
    untled
    0.85
    akable
    0.84
    ptive
    0.81
    essional
    0.78
    atives
    0.78
    achment
    0.77
    ptions
    0.76
    ruct
    0.75
    Act Density 0.039%

    No Known Activations