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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the letter 'n' in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.99
    DockStyle
    -0.98
    AndEndTag
    -0.98
     $_"
    -0.96
    setVerticalGroup
    -0.93
    ^(@)
    -0.92
     snippetHide
    -0.89
    AsUp
    -0.89
     ―――――
    -0.88
    fillType
    -0.86
    POSITIVE LOGITS
    n
    0.68
     n
    0.57
    N
    0.54
     
    0.51
     S
    0.50
     lo
    0.50
    nant
    0.50
    Vn
    0.50
    tosa
    0.49
    jen
    0.48
    Act Density 0.005%

    No Known Activations