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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply movement or directionality, particularly variations of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cree
    -0.68
     SSC
    -0.68
    ürd
    -0.64
    ley
    -0.61
    Scha
    -0.60
     Abonnez
    -0.59
    SSC
    -0.59
     Quảng
    -0.59
    ГЛА
    -0.59
     Bö
    -0.58
    POSITIVE LOGITS
    逅
    0.85
    cosm
    0.85
     referenties
    0.84
     виправивши
    0.83
    脚注の使い方
    0.83
     ]
    0.83
     الحره
    0.81
    thâu
    0.79
    migrationBuilder
    0.76
    unggulan
    0.76
    Act Density 0.303%

    No Known Activations