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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or negative feedback

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism directed towards individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTE
    -0.69
    bourne
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    seed
    -0.68
    nown
    -0.65
    cre
    -0.63
    ammy
    -0.63
    aho
    -0.63
    ipeg
    -0.61
    ther
    -0.61
    POSITIVE LOGITS
     harshly
    0.78
     Cosponsors
    0.78
     critiques
    0.72
    imaru
    0.72
     criticisms
    0.69
     criticized
    0.68
     criticizing
    0.67
     comments
    0.67
     harsh
    0.65
     criticism
    0.65
    Act Density 0.035%

    No Known Activations