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

    Neuronpedia

    INDEX
    Explanations

    terms related to national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.84
    Blocks
    -0.81
    oven
    -0.77
    unt
    -0.76
    Torrent
    -0.76
    bare
    -0.76
    chrom
    -0.74
    ken
    -0.74
     Refresh
    -0.73
     Niet
    -0.73
    POSITIVE LOGITS
     adviser
    1.10
     advisor
    1.07
     Advisor
    0.91
     Adviser
    0.90
     apparatus
    0.89
     implications
    0.89
     advisors
    0.87
     emergencies
    0.85
     interests
    0.85
     advisers
    0.84
    Act Density 0.024%

    No Known Activations