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

    Neuronpedia

    INDEX
    Explanations

    references to distance and travel between different places or cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pha
    -0.17
    xn
    -0.14
    erton
    -0.14
    ulla
    -0.14
    erosis
    -0.13
    ulton
    -0.13
    оÑģоб
    -0.13
    hong
    -0.13
    uga
    -0.13
    -One
    -0.13
    POSITIVE LOGITS
     thousands
    0.47
     Thousands
    0.37
     across
    0.35
     Across
    0.35
    Across
    0.35
     thousand
    0.34
    Thousands
    0.32
     hundreds
    0.30
    cross
    0.27
     crossed
    0.26
    Act Density 0.083%

    No Known Activations