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

    Neuronpedia

    INDEX
    Explanations

    references and citation details in academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.07
     ddelweddau
    -0.95
    ^(@)
    -0.94
     itſelf
    -0.93
     Efq
    -0.92
    ContentAlignment
    -0.85
     Monfieur
    -0.85
     becauſe
    -0.84
     ―――――
    -0.82
     Anſ
    -0.81
    POSITIVE LOGITS
    ever
    0.59
     ever
    0.59
    Ever
    0.54
    J
    0.51
     nieder
    0.50
    ::
    0.49
    :/
    0.49
    Me
    0.49
     corrientes
    0.48
     \\
    0.47
    Act Density 0.082%

    No Known Activations