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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases associated with scientific concepts and methods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    省市镇
    -0.65
     betekenis
    -0.59
     متعلقه
    -0.55
     Whigs
    -0.54
    stateProvider
    -0.54
    bitat
    -0.51
     Hubble
    -0.50
     mohair
    -0.49
    urther
    -0.49
     Blackstone
    -0.48
    POSITIVE LOGITS
     consist
    0.69
    Hauptartikel
    0.60
     consists
    0.56
     usually
    0.56
     involves
    0.56
     involve
    0.55
     DbType
    0.55
    retweet
    0.54
    êtement
    0.54
    CONSIN
    0.53
    Act Density 0.168%

    No Known Activations