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

    Neuronpedia

    INDEX
    Explanations

    references to groups or entities related to military alliances

    oai_token-act-pair · gpt-3.5-turbo

    references to Allied forces or alliances in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pered
    -0.84
    anity
    -0.84
    Hop
    -0.82
    hots
    -0.81
    gered
    -0.78
    nit
    -0.77
    obs
    -0.76
    fitting
    -0.76
    aminer
    -0.75
    ©¶æ
    -0.75
    POSITIVE LOGITS
     Forces
    0.96
     Powers
    0.82
     Allies
    0.82
     Allied
    0.80
    ãĤ¤ãĥĪ
    0.80
     Federation
    0.76
     sympath
    0.75
     parach
    0.73
     Organization
    0.72
     servic
    0.72
    Act Density 0.025%

    No Known Activations