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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to actions and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucc
    -0.17
    /moment
    -0.14
    olf
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    åĿª
    -0.14
     Duffy
    -0.14
    minor
    -0.14
    еÑĢÑĪ
    -0.14
    æ¹¾
    -0.14
     WON
    -0.13
    POSITIVE LOGITS
    ÙİاÙĨ
    0.18
    ogui
    0.16
    ycz
    0.15
    Å¡il
    0.15
    etter
    0.15
    Borders
    0.15
     doz
    0.14
    zyst
    0.14
    yne
    0.14
    /is
    0.14
    Act Density 0.186%

    No Known Activations