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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various societal and global issues

    oai_token-act-pair · gpt-3.5-turbo

    words related to various social issues and environmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '.
    -0.53
    SY
    -0.52
    ".[
    -0.52
    CLASSIFIED
    -0.52
    '.
    -0.51
    .).
    -0.49
    !".
    -0.49
    "!
    -0.49
    irlf
    -0.47
     theirs
    -0.47
    POSITIVE LOGITS
     varies
    0.79
     depends
    0.78
     involves
    0.75
     coincided
    0.74
     constitutes
    0.74
     arises
    0.73
     depended
    0.73
     coincides
    0.70
     implies
    0.69
     outweigh
    0.68
    Act Density 1.153%

    No Known Activations