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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     же
    -0.15
    <strong
    -0.14
    UAL
    -0.14
    lef
    -0.14
    omat
    -0.14
    ÏĦεÏģ
    -0.13
    recht
    -0.13
    AGO
    -0.13
    ated
    -0.13
    ago
    -0.13
    POSITIVE LOGITS
     info
    0.27
     specifically
    0.26
     Info
    0.24
     details
    0.22
     information
    0.21
    house
    0.20
     precisely
    0.20
    tz
    0.19
    ä¿¡æģ¯
    0.19
    au
    0.19
    Act Density 0.050%

    No Known Activations