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

    Neuronpedia

    INDEX
    Explanations

    ellipses or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.85
     flourishing
    -0.69
     observers
    -0.68
    ratulations
    -0.65
     stagger
    -0.65
    hiba
    -0.63
    guards
    -0.63
     prosperity
    -0.63
    Ļ½
    -0.63
     chilling
    -0.62
    POSITIVE LOGITS
    tml
    0.83
    =#
    0.79
    dp
    0.77
    pic
    0.74
     Retrieved
    0.74
    toc
    0.72
    ection
    0.71
    doi
    0.69
    eur
    0.69
    arget
    0.68
    Act Density 0.006%

    No Known Activations