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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and instructional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reminder
    -0.16
    ÑĩиÑħ
    -0.16
    etections
    -0.15
    ignet
    -0.15
    /manual
    -0.14
    cem
    -0.14
     âĹĦ
    -0.14
    ctp
    -0.14
     rov
    -0.13
    ìľµ
    -0.13
    POSITIVE LOGITS
     tips
    0.33
    tips
    0.27
     tip
    0.26
     Tips
    0.23
     how
    0.23
     Tip
    0.22
    tip
    0.21
    Tips
    0.20
    -tip
    0.20
     best
    0.19
    Act Density 0.170%

    No Known Activations