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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.51
    bootstrapcdn
    -0.48
    )».
    -0.47
    angliski
    -0.46
     gubern
    -0.46
    expandindo
    -0.46
     Paglinawan
    -0.45
    invokeLater
    -0.45
     '\\;'
    -0.44
     خارجية
    -0.43
    POSITIVE LOGITS
    something
    0.53
     mierda
    0.48
    maybe
    0.47
     maybe
    0.47
    silly
    0.46
     sowas
    0.46
     silly
    0.44
    somebody
    0.44
     yeah
    0.44
     somebody
    0.44
    Act Density 0.539%

    No Known Activations