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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expected behavior or outcomes in a testing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المناصب
    -1.01
     '\\;'
    -0.94
    клопе
    -0.93
    (;;)
    -0.91
    WriteBarrier
    -0.89
    NUMX
    -0.88
    ]")]
    -0.88
    URLException
    -0.86
    '])){
    -0.85
     nonUne
    -0.84
    POSITIVE LOGITS
    should
    1.05
     should
    0.88
    Should
    0.85
     Should
    0.75
     SHOULD
    0.69
    assertThat
    0.64
     shouldn
    0.60
     must
    0.59
     might
    0.58
    may
    0.57
    Act Density 0.045%

    No Known Activations