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

    Neuronpedia

    INDEX
    Explanations

    references to specific research studies and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic citations and publication years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.75
    arnaev
    -0.74
    TextColor
    -0.71
    justice
    -0.71
    ongs
    -0.69
    isec
    -0.68
    udeb
    -0.65
     regiment
    -0.64
    pport
    -0.64
    mir
    -0.63
    POSITIVE LOGITS
     ).
    0.79
    å¹
    0.78
    )—
    0.76
    ).
    0.76
    )).
    0.74
     ),
    0.71
     PhD
    0.70
    ):
    0.70
     pp
    0.70
    published
    0.69
    Act Density 0.049%

    No Known Activations