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

    Neuronpedia

    INDEX
    Explanations

    mentions of military ranks

    oai_token-act-pair · gpt-3.5-turbo

    the mention of military ranks or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLE
    -0.79
    perate
    -0.72
     damned
    -0.69
     predictably
    -0.66
    earchers
    -0.63
    fitted
    -0.63
     Vaugh
    -0.63
    fm
    -0.63
    FAULT
    -0.63
     Machina
    -0.62
    POSITIVE LOGITS
    itized
    0.90
     depressive
    0.75
    minster
    0.74
     League
    0.71
    isd
    0.70
    leaf
    0.69
    ificant
    0.68
    itarian
    0.68
    nton
    0.68
    TAIN
    0.66
    Act Density 0.013%

    No Known Activations