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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversial or sensitive topics, including political conflicts and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.77
    uncture
    -0.76
    oire
    -0.75
    bara
    -0.74
    atform
    -0.73
    iologist
    -0.71
    enance
    -0.71
    iasco
    -0.69
    ebin
    -0.68
    ruption
    -0.68
    POSITIVE LOGITS
     replacements
    1.28
     selves
    1.23
     losers
    1.22
     ambassadors
    1.22
     slaves
    1.21
    selves
    1.17
     heroes
    1.16
     combatants
    1.15
     pioneers
    1.15
     carriers
    1.13
    Act Density 0.383%

    No Known Activations