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

    Neuronpedia

    INDEX
    Explanations

    references to legal issues and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PyObject
    -0.66
     gynnwys
    -0.58
    ropoda
    -0.55
    phalt
    -0.55
     $_"
    -0.55
    +#+#
    -0.54
    SizeMode
    -0.53
     المعرف
    -0.53
     Passe
    -0.52
    νά
    -0.52
    POSITIVE LOGITS
     violates
    0.52
     prematurely
    0.51
     forbidden
    0.49
     contrary
    0.49
     risking
    0.49
    TagHelper
    0.49
     violating
    0.47
    paio
    0.47
     unauthorized
    0.46
     risked
    0.45
    Act Density 0.624%

    No Known Activations