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

    Neuronpedia

    INDEX
    Explanations

    technical terms or topics related to technology and science

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shroud
    -0.77
     wool
    -0.72
     companion
    -0.68
     outweigh
    -0.67
     dwarf
    -0.67
     sanctuary
    -0.67
     barrier
    -0.66
     hol
    -0.65
     AMERICA
    -0.64
     polyg
    -0.64
    POSITIVE LOGITS
    roximately
    1.18
    resa
    1.11
    icularly
    1.05
    aring
    1.02
    rary
    1.01
    itionally
    1.01
    inguished
    0.99
    inct
    0.99
    withstanding
    0.99
    asionally
    0.97
    Act Density 0.212%

    No Known Activations