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

    Neuronpedia

    INDEX
    Explanations

    specific numerical patterns or sequences within data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Tr
    -0.53
     Administrativna
    -0.53
     Saints
    -0.53
     longer
    -0.51
    стей
    -0.51
     Tre
    -0.51
     CONT
    -0.51
    leg
    -0.50
    Eloquent
    -0.50
    oben
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.74
     AssemblyTitle
    0.68
    AssignableFrom
    0.66
    DOCTYPE
    0.65
    \{\\
    0.62
    PyExc
    0.62
     rêver
    0.62
     extérieurs
    0.60
    нодоро
    0.58
     digitais
    0.57
    Act Density 0.001%

    No Known Activations