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

    Neuronpedia

    INDEX
    Explanations

    units of measurement or values related to quantities and concentrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </strong>
    -2.80
    </em>
    -2.52
    <strong>
    -1.99
    <em>
    -1.81
     
    -1.17
    """
    -1.04
    "<<
    -1.02
    ",@"
    -1.01
     fi
    -1.00
    """
    -1.00
    POSITIVE LOGITS
    </b>
    2.83
    </i>
    2.71
    <b>
    1.66
    dfrac
    1.66
    <i>
    1.59
     × 
    1.58
      
    1.56
     + 
    1.53
     = 
    1.53
     ± 
    1.52
    Act Density 0.306%

    No Known Activations