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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of rejection or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utton
    -0.19
    _lifetime
    -0.16
    raith
    -0.16
    _PM
    -0.15
    aylight
    -0.15
    SCRI
    -0.14
     lifetime
    -0.14
    ucken
    -0.14
    å¥ı
    -0.14
    enko
    -0.13
    POSITIVE LOGITS
    मह
    0.15
    oni
    0.15
     lev
    0.15
    FFT
    0.15
    -dess
    0.14
     comm
    0.14
     Roy
    0.13
     Courier
    0.13
    su
    0.13
     anom
    0.13
    Act Density 0.026%

    No Known Activations