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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    individual letters or single-character variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Measure
    -0.72
     convol
    -0.67
     subtract
    -0.64
     dispatcher
    -0.64
     feder
    -0.63
     cryst
    -0.63
    CHO
    -0.62
    editor
    -0.60
     depress
    -0.59
    ept
    -0.59
    POSITIVE LOGITS
    uala
    0.94
    shi
    0.93
    icz
    0.85
    ian
    0.84
    ius
    0.80
    ÃŃa
    0.79
    ny
    0.77
    itic
    0.77
    itsch
    0.77
    nikov
    0.75
    Act Density 0.186%

    No Known Activations