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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strategies or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to structured plans or protocols, particularly in a legal or strategic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.77
    umph
    -0.74
    inth
    -0.71
    orescent
    -0.69
    shall
    -0.69
    birth
    -0.68
    ho
    -0.68
    enny
    -0.67
     anonymity
    -0.67
    iden
    -0.67
    POSITIVE LOGITS
     playbook
    1.61
    æ©
    1.03
     Blueprint
    0.87
    naire
    0.87
    ãĥ¼ãĥĨ
    0.82
    book
    0.81
     blueprint
    0.79
     checklist
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.76
    æ©Ł
    0.76
    Act Density 0.024%

    No Known Activations