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

    Neuronpedia

    INDEX
    Explanations

    unrelated characters or artifacts in the text

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with a high level of numerical or financial significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occas
    -0.82
     framing
    -0.81
     eleph
    -0.81
     undermin
    -0.79
     favoring
    -0.76
    aditional
    -0.73
     aging
    -0.73
     favorably
    -0.73
     inactive
    -0.71
     favors
    -0.71
    POSITIVE LOGITS
    Scroll
    1.00
    Liverpool
    0.96
    BBC
    0.95
    Labour
    0.90
    Royal
    0.83
    Els
    0.82
    ³³³³³³³³³³³³³³³³
    0.81
    iona
    0.81
    Manchester
    0.79
    DragonMagazine
    0.79
    Act Density 0.346%

    No Known Activations