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

    Neuronpedia

    INDEX
    Explanations

    politically sensitive phrases and discussions surrounding social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.63
     Tsukuyomi
    -0.62
    Tonight
    -0.61
    Interstitial
    -0.61
     "<
    -0.61
     ILCS
    -0.61
     Conquer
    -0.60
    ructose
    -0.59
    [_
    -0.59
     ItemLevel
    -0.59
    POSITIVE LOGITS
     consideration
    0.83
    ilyn
    0.82
     factor
    0.82
     besides
    0.81
     noteworthy
    0.79
     relates
    0.78
    worldly
    0.75
     involves
    0.75
    orthy
    0.71
    mentioned
    0.71
    Act Density 0.156%

    No Known Activations