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

    Neuronpedia

    INDEX
    Explanations

    controversial and polarizing issues or actions involving various groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okin
    -0.54
    IRC
    -0.52
    GN
    -0.51
     unfocusedRange
    -0.51
    addon
    -0.49
     confir
    -0.48
     referen
    -0.48
     millenn
    -0.48
    Indust
    -0.47
     Hawks
    -0.46
    POSITIVE LOGITS
    .''.
    0.77
    .;
    0.73
    !.
    0.72
     whilst
    0.71
    .</
    0.71
    .",
    0.67
     lest
    0.66
     etc
    0.66
    .–
    0.66
    .
    0.65
    Act Density 0.956%

    No Known Activations