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

    Neuronpedia

    INDEX
    Explanations

    instances of negative commentary or criticism in context

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

    Criticism or opposition

    np_acts-logits-general · gemini-2.0-flash

    criticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onOptions
    -0.64
     StatefulWidget
    -0.55
     morire
    -0.48
    esModule
    -0.46
    dotenv
    -0.45
    ProcessEvent
    -0.44
    TemporalType
    -0.44
     confirme
    -0.44
     رع
    -0.43
    ervis
    -0.43
    POSITIVE LOGITS
     criticism
    2.14
     criticize
    1.92
     criticisms
    1.86
     critique
    1.84
     criticizing
    1.82
     criticise
    1.76
     Criticism
    1.75
     critic
    1.74
     critici
    1.74
     criti
    1.71
    Act Density 0.580%

    No Known Activations