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

    Neuronpedia

    INDEX
    Explanations

    chemical symbols and concentration measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     […]
    -1.74
    […]
    -1.44
    …
    -0.92
     [...]
    -0.91
      
    -0.88
    [...]
    -0.87
    <sup>
    -0.84
     = 
    -0.81
    (…)
    -0.78
     (…)
    -0.78
    POSITIVE LOGITS
     ~
    1.19
    '~
    1.19
    ~
    1.17
    ·
    1.15
    ,~
    1.15
    .~
    1.11
    ~.
    1.10
    ~,
    1.10
    -~
    1.04
     '~
    1.02
    Act Density 0.589%

    No Known Activations