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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duit
    -0.16
     Plains
    -0.15
     Shore
    -0.15
     interiors
    -0.14
     inland
    -0.14
     jedn
    -0.14
     ceilings
    -0.14
    æĿī
    -0.14
     Sour
    -0.14
     Summit
    -0.13
    POSITIVE LOGITS
     surf
    0.20
     waves
    0.18
     fo
    0.17
     wave
    0.17
     beach
    0.17
     shallow
    0.17
     prom
    0.16
    çłģ
    0.16
     sand
    0.16
    COPE
    0.16
    Act Density 0.368%

    No Known Activations