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

    Neuronpedia

    INDEX
    Explanations

    certain characters or character combinations within the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.97
     adolesc
    -0.81
    ufact
    -0.77
     carbohyd
    -0.74
     scrut
    -0.74
    auga
    -0.74
    ntil
    -0.73
     agre
    -0.72
    yip
    -0.71
     oun
    -0.70
    POSITIVE LOGITS
    ×ķ
    0.95
    ł
    0.92
    ï¸ı
    0.88
    ×Ļ×
    0.87
    Ñĥ
    0.81
    ãĥ¼ãĥ³
    0.80
    ा
    0.78
    ople
    0.78
    ķ
    0.76
    hens
    0.75
    Act Density 0.008%

    No Known Activations