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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary material in scientific documentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    UserScript
    -0.77
     <<<<<<<<<<<<<<
    -0.70
     kasarigan
    -0.68
     Shaksp
    -0.67
     iſt
    -0.67
     purpoſe
    -0.66
    interopRequire
    -0.66
     Perſ
    -0.64
     poffible
    -0.63
     Descriptors
    -0.62
    POSITIVE LOGITS
    oa̍t
    0.47
    WithValue
    0.46
    jedis
    0.45
    []"
    0.44
    ag
    0.44
     A
    0.44
    roppo
    0.42
    hoeddwyd
    0.42
    สูง
    0.42
     ostavi
    0.41
    Act Density 0.002%

    No Known Activations