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

    Neuronpedia

    INDEX
    Explanations

    instances of criticism or critical commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    criticism and scolding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.51
    fromnode
    -0.49
    ंदीखरीदारी
    -0.49
    complexContent
    -0.48
     везе
    -0.46
    contentLoaded
    -0.46
     IFTT
    -0.46
     uVar
    -0.46
     snippetHide
    -0.45
    تقاوى
    -0.44
    POSITIVE LOGITS
     criticized
    0.74
     criticizing
    0.69
     admon
    0.68
     criticised
    0.65
     rebuke
    0.60
     criticize
    0.59
     criticism
    0.58
     criticisms
    0.58
     Criticism
    0.56
     scolded
    0.56
    Act Density 0.023%

    No Known Activations