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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adele
    -0.16
    ties
    -0.16
    usercontent
    -0.15
    ively
    -0.14
    kil
    -0.14
    fal
    -0.14
    ight
    -0.14
    ilm
    -0.14
    ãĤĪãģĨãģª
    -0.14
    andard
    -0.14
    POSITIVE LOGITS
    geries
    0.28
    bidden
    0.27
     sake
    0.27
    -profit
    0.26
    /by
    0.24
     instance
    0.23
    aging
    0.22
     purposes
    0.21
    age
    0.21
    /about
    0.21
    Act Density 0.720%

    No Known Activations