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

    Neuronpedia

    INDEX
    Explanations

    references to review processes, figures, and reviewer comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.89
     ¨
    -0.84
     ‎
    -0.84
     ´
    -0.83
     ‘’
    -0.81
    .
    -0.81
    
    -0.80
     ♥
    -0.80
    ‎
    -0.79
    ‍
    -0.79
    POSITIVE LOGITS
     $\$
    1.68
     $\
    1.68
     \&
    1.47
     $\&$
    1.46
     $=$
    1.41
     $=\
    1.38
     $\%
    1.38
     $=
    1.38
     $(\
    1.37
     $\%$
    1.35
    Act Density 1.480%

    No Known Activations