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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perpetuating negative actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    political or social critique, particularly regarding support for certain agendas or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.75
    eline
    -0.73
     appreciated
    -0.70
    DragonMagazine
    -0.67
     survived
    -0.66
    tackle
    -0.66
    Clear
    -0.65
    imentary
    -0.65
    fax
    -0.65
     thanked
    -0.65
    POSITIVE LOGITS
     false
    1.16
     harmful
    1.16
     inaccurate
    1.15
     misinformation
    1.15
     falsehood
    1.13
     misleading
    1.12
     unrealistic
    1.11
     irresponsible
    1.11
     distorted
    1.09
     incorrect
    1.08
    Act Density 1.703%

    No Known Activations