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

    Neuronpedia

    INDEX
    Explanations

    phrases inviting or encouraging engagement with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.74
    ragon
    -0.70
    ected
    -0.70
    bably
    -0.68
    urdue
    -0.67
    ãĥł
    -0.65
    posed
    -0.64
    aturated
    -0.64
    IDS
    -0.64
    fixed
    -0.63
    POSITIVE LOGITS
     More
    0.82
    chu
    0.82
     MORE
    0.76
    Article
    0.74
    ers
    0.70
    ership
    0.67
    About
    0.67
     ABOUT
    0.66
     Less
    0.65
    about
    0.65
    Act Density 0.120%

    No Known Activations