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

    Neuronpedia

    INDEX
    Explanations

    instances of the token "sa" with varying frequency

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

    sa/SA prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    diad
    -0.49
    $\%
    -0.47
    Diwedd
    -0.46
    CCCC
    -0.45
    "/>
    -0.45
    ////////////////
    -0.44
    (['/
    -0.43
    ="/">
    -0.43
    arschijnlijk
    -0.42
     "/")
    -0.42
    POSITIVE LOGITS
    sa
    2.06
    Sa
    1.45
     Sa
    1.45
     sa
    1.42
     SA
    0.94
    SA
    0.88
    saa
    0.81
    Sae
    0.81
     Sahib
    0.77
     sails
    0.71
    Act Density 0.004%

    No Known Activations