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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal or harmful actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to acts of committing crimes or harmful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    framework
    -0.78
     Remastered
    -0.77
    iewicz
    -0.69
     complexion
    -0.68
    gypt
    -0.67
    net
    -0.67
    clinton
    -0.66
    nas
    -0.65
    iris
    -0.63
    issue
    -0.63
    POSITIVE LOGITS
     suicide
    1.44
     adultery
    1.26
     atrocities
    1.25
     perjury
    1.23
     crimes
    1.22
     offences
    1.17
     treason
    1.17
     heinous
    1.14
     arson
    1.12
     fraud
    1.10
    Act Density 0.040%

    No Known Activations