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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political issues and positions

    oai_token-act-pair · gpt-3.5-turbo

    references to ethical dilemmas involving life and death situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦)
    -0.59
    ...)
    -0.58
    !)
    -0.57
    -)
    -0.56
    )"
    -0.55
     *)
    -0.54
    ;}
    -0.53
     Dise
    -0.53
     gener
    -0.53
    Loading
    -0.52
    POSITIVE LOGITS
    etheless
    0.95
     Trotsky
    0.60
     âĵĺ
    0.59
    AFP
    0.58
    tower
    0.55
     Pruitt
    0.54
    iannopoulos
    0.54
    collect
    0.54
     Glacier
    0.53
     Stalin
    0.53
    Act Density 3.361%

    No Known Activations