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

    Neuronpedia

    INDEX
    Explanations

    commands, directives or urgent instructions

    oai_token-act-pair · gpt-3.5-turbo

    commands or urgent requests for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weet
    -0.81
    LGBT
    -0.74
    olkien
    -0.74
    uably
    -0.73
     millennial
    -0.73
     embraced
    -0.73
    ibia
    -0.73
    onut
    -0.72
    iqueness
    -0.70
     stereotyp
    -0.70
    POSITIVE LOGITS
     reinforcements
    1.25
     Militia
    1.20
     evacuate
    1.08
     evac
    1.07
     patrol
    1.06
     Lieutenant
    1.04
     patrols
    1.03
     Ops
    1.03
     supplies
    1.03
     convoy
    1.02
    Act Density 0.792%

    No Known Activations