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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deserving or worthy individuals or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express worthiness or deserving of recognition and praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nel
    -0.74
    ullivan
    -0.74
    nels
    -0.72
    lems
    -0.65
     barriers
    -0.65
     stru
    -0.64
    isms
    -0.63
     weeds
    -0.63
     processes
    -0.62
     portals
    -0.62
    POSITIVE LOGITS
     scorn
    0.91
     praise
    0.88
    $$$$
    0.86
    cellence
    0.79
     ridicule
    0.77
    EDIT
    0.77
    ENTION
    0.76
     criticism
    0.74
    udos
    0.74
     scrutiny
    0.72
    Act Density 0.105%

    No Known Activations