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

    Neuronpedia

    INDEX
    Explanations

    themes related to political ideologies, specifically -ism suffixes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various ideologies and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TAIN
    -0.83
    ergy
    -0.76
    VID
    -0.71
    FACE
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
    âĸ¬âĸ¬
    -0.66
    vag
    -0.66
     Kardash
    -0.65
    Lear
    -0.64
     allerg
    -0.63
    POSITIVE LOGITS
    yip
    1.10
    atics
    1.03
    atism
    1.00
    ism
    0.99
    atic
    0.87
    ische
    0.84
    anism
    0.84
    anship
    0.84
    ophobia
    0.83
    ophical
    0.82
    Act Density 0.028%

    No Known Activations