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

    Neuronpedia

    INDEX
    Explanations

    references to certain locations or entities, particularly those associated with the letter "H" or nearby identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajan
    -0.15
    isser
    -0.14
    san
    -0.14
    resident
    -0.14
     Hom
    -0.14
    tribute
    -0.14
    rowsable
    -0.13
     Ho
    -0.13
     Schwarz
    -0.13
     ho
    -0.13
    POSITIVE LOGITS
    ert
    0.28
    erts
    0.28
    engo
    0.26
    oun
    0.21
    umber
    0.21
    agger
    0.20
    ibern
    0.20
    ants
    0.19
    ighb
    0.19
    udd
    0.19
    Act Density 0.010%

    No Known Activations