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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "world" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    nze
    -0.14
    olian
    -0.14
    wares
    -0.14
    LEAR
    -0.14
    ỡ
    -0.14
     mex
    -0.13
     Bik
    -0.13
    çļ
    -0.13
    ì§Ī
    -0.13
    POSITIVE LOGITS
    tracer
    0.17
    fuse
    0.16
    interpret
    0.14
     Martial
    0.14
    rán
    0.14
    uss
    0.14
    onu
    0.14
    inous
    0.14
     Occupy
    0.13
    ê¸ī
    0.13
    Act Density 0.018%

    No Known Activations