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

    Neuronpedia

    INDEX
    Explanations

    terms related to representation and diversity within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.39
     gyhoeddwyd
    -0.37
     Италијани
    -0.36
    SourceChecksum
    -0.35
    GTCX
    -0.33
    TagMode
    -0.32
    ỡng
    -0.31
    ñador
    -0.30
     Marín
    -0.30
    ziplin
    -0.30
    POSITIVE LOGITS
     representation
    3.41
     REPRESENT
    3.23
     representative
    3.22
     Representation
    3.06
    represent
    3.03
     represented
    3.03
     represent
    3.00
     representa
    2.98
    Represent
    2.97
     represen
    2.97
    Act Density 0.747%

    No Known Activations