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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    807
    -0.15
    uti
    -0.15
    Obs
    -0.14
    estination
    -0.14
    ource
    -0.14
     Obs
    -0.14
    oug
    -0.13
    lightbox
    -0.13
    inate
    -0.13
    nin
    -0.13
    POSITIVE LOGITS
    åºľ
    0.17
    anse
    0.17
    为äºĨ
    0.16
    SG
    0.15
     afin
    0.15
     inorder
    0.14
    uo
    0.14
     nhằm
    0.13
    sty
    0.13
     ÑĩÑĤобÑĭ
    0.13
    Act Density 0.346%

    No Known Activations