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

    Neuronpedia

    INDEX
    Explanations

    fragments of programming code and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']=$
    -0.58
     ex
    -0.52
    \}=
    -0.52
    )}-\
    -0.47
     $\
    -0.47
     Sha
    -0.46
     Gre
    -0.45
    '],'
    -0.45
    ]='\
    -0.45
    –)
    -0.45
    POSITIVE LOGITS
    Datuak
    0.84
     архивлан
    0.75
    Jîn
    0.73
     Efq
    0.70
    numerusform
    0.69
     civile
    0.69
    ExtendWith
    0.68
     defStyle
    0.66
    TargetException
    0.66
     thorium
    0.65
    Act Density 0.025%

    No Known Activations