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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilm
    -0.17
    ties
    -0.16
    gren
    -0.15
    usercontent
    -0.15
    adele
    -0.15
    ively
    -0.15
    mite
    -0.15
    ãĤĪãģĨãģª
    -0.15
    mh
    -0.14
    ka
    -0.14
    POSITIVE LOGITS
     sake
    0.26
    bidden
    0.26
    geries
    0.25
    -profit
    0.24
    /by
    0.23
     instance
    0.21
    aging
    0.20
     purposes
    0.20
    /from
    0.19
    /about
    0.19
    Act Density 0.716%

    No Known Activations