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

    Neuronpedia

    INDEX
    Explanations

    statements of belief or persuasion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political or societal beliefs and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partName
    -0.66
    EMS
    -0.60
    Attempts
    -0.60
     sqor
    -0.56
    geoning
    -0.56
    mentioned
    -0.54
    assuming
    -0.54
     largeDownload
    -0.54
     sidx
    -0.52
    iHUD
    -0.51
    POSITIVE LOGITS
     immoral
    0.72
     somehow
    0.69
     daddy
    0.67
     someday
    0.67
     rapists
    0.66
     raping
    0.63
     pedoph
    0.62
     homosexuals
    0.62
     ruining
    0.62
     "'
    0.61
    Act Density 1.079%

    No Known Activations