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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $=
    -0.55
    stanza
    -0.52
     tetanus
    -0.51
     Intelligen
    -0.50
     Bask
    -0.50
    iculture
    -0.50
     Penalties
    -0.49
    ANTON
    -0.48
     exemptions
    -0.47
     ():
    -0.47
    POSITIVE LOGITS
    <bos>
    2.87
     '\\;'
    0.59
    /**
    0.58
     مواليد
    0.57
     the
    0.57
    /*
    0.56
    #
    0.55
    __':
    0.55
    ècie
    0.55
    Autoritní
    0.54
    Act Density 4.105%

    No Known Activations