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

    Neuronpedia

    INDEX
    Explanations

    elements related to exploration and navigation in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieber
    -0.15
    ipur
    -0.14
    ãĤ¤ãĤº
    -0.14
    缼
    -0.14
    uppy
    -0.14
    olik
    -0.14
     incl
    -0.14
    phia
    -0.13
    è£ģ
    -0.13
    laden
    -0.13
    POSITIVE LOGITS
     exploration
    0.30
     explores
    0.29
     exploring
    0.29
     explore
    0.28
     explor
    0.26
     travers
    0.26
     navig
    0.26
     Exploration
    0.25
     explored
    0.25
    Explore
    0.24
    Act Density 0.295%

    No Known Activations