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

    Neuronpedia

    INDEX
    Explanations

    concepts related to conflict or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating responsibility or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è»
    -0.60
    oult
    -0.59
    earchers
    -0.59
    icious
    -0.57
    Browser
    -0.55
    çīĪ
    -0.55
     anecd
    -0.54
    eday
    -0.54
    oother
    -0.54
    named
    -0.52
    POSITIVE LOGITS
     mankind
    0.79
     humankind
    0.77
     Capitalism
    0.67
     humanity
    0.67
     civilisation
    0.65
     capitalism
    0.63
     Iran
    0.63
     Catalonia
    0.63
     our
    0.62
     Islam
    0.62
    Act Density 0.579%

    No Known Activations