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

    Neuronpedia

    INDEX
    Explanations

    themes related to relationships and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¦ĥ
    -0.14
    好çļĦ
    -0.13
    ÑĢик
    -0.13
    ahir
    -0.13
    ëĭµ
    -0.13
    idable
    -0.13
    vero
    -0.12
    688
    -0.12
    opsy
    -0.12
    387
    -0.12
    POSITIVE LOGITS
     thing
    0.88
    thing
    0.65
     Thing
    0.65
     stuff
    0.60
    Thing
    0.54
     cosa
    0.45
     coisa
    0.42
    stuff
    0.42
     things
    0.42
     Stuff
    0.41
    Act Density 0.430%

    No Known Activations