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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or concepts throughout the text

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

    again or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conmigo
    -0.40
     puol
    -0.38
    Gweler
    -0.37
    țional
    -0.36
     kiin
    -0.34
    alyptus
    -0.33
     Sécurité
    -0.33
     Presidencia
    -0.33
     abuelo
    -0.32
     Auß
    -0.31
    POSITIVE LOGITS
    again
    0.82
     Again
    0.82
    Again
    0.80
     again
    0.75
     AGAIN
    0.75
    又是一
    0.69
    又要
    0.67
    又是
    0.65
     erneut
    0.65
     опять
    0.65
    Act Density 0.149%

    No Known Activations