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

    Neuronpedia

    INDEX
    Explanations

    phrases related to renovations and improvements in structures or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«ãĥĪ
    -0.16
    IMP
    -0.15
    lon
    -0.15
    ending
    -0.14
    loon
    -0.14
     dead
    -0.14
    .mapping
    -0.14
     crack
    -0.13
    ends
    -0.13
    lox
    -0.13
    POSITIVE LOGITS
    ainen
    0.16
    ypi
    0.16
     Pier
    0.15
    viders
    0.15
    Ïģιν
    0.15
    blas
    0.15
    vang
    0.15
     Wend
    0.15
    bjerg
    0.15
    ognito
    0.14
    Act Density 0.256%

    No Known Activations