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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-perception and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    assigns status or judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étrangères
    -0.51
     Inſ
    -0.50
     reaſon
    -0.49
     prêtres
    -0.49
     purpoſe
    -0.48
     Keuangan
    -0.46
     ſche
    -0.45
     Eſ
    -0.45
     houſe
    -0.45
     numériques
    -0.44
    POSITIVE LOGITS
     considers
    0.85
     Considered
    0.82
     considered
    0.82
    considered
    0.81
     consider
    0.79
    consider
    0.79
     CONSIDER
    0.75
     considera
    0.75
     Consider
    0.75
    Consider
    0.70
    Act Density 0.033%

    No Known Activations