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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional items or examples in a list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reconciliation
    -0.15
     Dare
    -0.15
    ROP
    -0.15
    ries
    -0.14
    upy
    -0.14
     Anast
    -0.14
    .Args
    -0.14
    .grp
    -0.13
     addCriterion
    -0.13
    nik
    -0.13
    POSITIVE LOGITS
    thing
    0.15
    gether
    0.15
    Assembler
    0.14
    quier
    0.14
    nts
    0.14
     BITS
    0.14
    strstr
    0.14
     Inf
    0.14
    lesh
    0.14
    мп
    0.14
    Act Density 0.011%

    No Known Activations