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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security threats and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to threats and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Character
    -0.79
    itone
    -0.78
     Citation
    -0.76
    Story
    -0.76
    éĹĺ
    -0.76
    tone
    -0.75
    ãģĨ
    -0.75
    ridor
    -0.75
    examination
    -0.74
    folio
    -0.74
    POSITIVE LOGITS
     rapists
    1.42
     terrorists
    1.36
     dictators
    1.32
     murderers
    1.32
     criminals
    1.31
     fascists
    1.31
     dissidents
    1.31
     thugs
    1.30
     mercenaries
    1.30
     racists
    1.28
    Act Density 0.229%

    No Known Activations