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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nuclear programs or weapons, particularly in relation to Iran

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    steen
    -0.84
     Orth
    -0.79
     Hitchcock
    -0.78
    MpServer
    -0.74
    DIT
    -0.74
    Zip
    -0.73
    cms
    -0.73
    Baltimore
    -0.72
    annel
    -0.72
    emetery
    -0.71
    POSITIVE LOGITS
     missile
    0.99
     weapons
    0.93
     missiles
    0.91
     arsenal
    0.90
    weapons
    0.89
     warheads
    0.88
     disarm
    0.87
     bombing
    0.87
     treaty
    0.85
     regime
    0.85
    Act Density 0.097%

    No Known Activations