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

    Neuronpedia

    INDEX
    Explanations

    references to opinions or attitudes related to political polarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ïĥκε
    -0.16
    skirts
    -0.15
    -legged
    -0.15
    лоп
    -0.15
    akest
    -0.14
    ovatel
    -0.14
     serialVersionUID
    -0.14
    isclosed
    -0.14
    _hierarchy
    -0.14
     stripslashes
    -0.14
    POSITIVE LOGITS
     limit
    0.21
     mark
    0.18
     bitter
    0.18
     bone
    0.18
     wire
    0.17
     moon
    0.17
     finish
    0.16
    ablo
    0.16
    wire
    0.15
     curb
    0.15
    Act Density 0.099%

    No Known Activations