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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs marked by a specific token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.56
     jun
    -0.52
    TabIndex
    -0.50
     aigu
    -0.48
     hObject
    -0.47
     formal
    -0.46
    TagHelpers
    -0.44
    SPECTION
    -0.43
     baj
    -0.43
    เด
    -0.42
    POSITIVE LOGITS
    riwal
    0.73
     Montagne
    0.68
     Jefus
    0.68
     bezeichneter
    0.65
     Himalaya
    0.65
     Efq
    0.65
     raiſ
    0.65
     ſtand
    0.64
     neceff
    0.62
    antaranya
    0.62
    Act Density 0.032%

    No Known Activations