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

    Neuronpedia

    INDEX
    Explanations

    news headlines reporting actions or events involving various organizations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of authority or actions taken by organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.82
     behold
    -0.68
    ãĤ·ãĥ£
    -0.67
    cit
    -0.65
     immersion
    -0.63
    ually
    -0.62
     Radiant
    -0.62
     territ
    -0.62
     Mechanical
    -0.60
     inexper
    -0.60
    POSITIVE LOGITS
    zbollah
    0.80
     pleased
    0.77
     criticised
    0.75
     reportedly
    0.75
     stoked
    0.75
     unveiled
    0.74
     apologised
    0.72
     urged
    0.71
    senal
    0.70
     been
    0.70
    Act Density 0.365%

    No Known Activations