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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or judgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to judgment or evaluation of people, policies, or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.69
     Milky
    -0.63
    rontal
    -0.63
    ettlement
    -0.59
    oya
    -0.56
    abiding
    -0.55
    ipeg
    -0.55
    ggies
    -0.54
    rez
    -0.54
    rouse
    -0.54
    POSITIVE LOGITS
     favorably
    1.01
     unfairly
    0.98
     skept
    0.92
     harshly
    0.79
    Reviewer
    0.79
    igated
    0.72
     by
    0.71
    graded
    0.70
    Ú
    0.70
     merciless
    0.70
    Act Density 0.137%

    No Known Activations