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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.91
     fascic
    -0.78
     quæ
    -0.78
     auffi
    -0.76
     fevere
    -0.75
     respeito
    -0.74
     myſelf
    -0.74
    ſelves
    -0.72
     Scro
    -0.71
    WriteBarrier
    -0.70
    POSITIVE LOGITS
     “
    0.77
     The
    0.72
     way
    0.71
    ]<<"
    0.70
     the
    0.64
     no
    0.63
     empty
    0.63
     "
    0.62
     No
    0.62
    ]));
    0.62
    Act Density 0.134%

    No Known Activations