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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate equivalency and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pesan
    -0.14
    تÙĪر
    -0.14
    /animate
    -0.14
    dept
    -0.14
    anca
    -0.14
    rve
    -0.13
    lue
    -0.13
    .reserve
    -0.13
    ENUM
    -0.13
    Encoding
    -0.13
    POSITIVE LOGITS
     equivalent
    0.30
     Equivalent
    0.26
    Equivalent
    0.20
     identical
    0.20
     equivalents
    0.20
     converted
    0.18
    Converted
    0.18
     equival
    0.17
    -equ
    0.17
     equal
    0.17
    Act Density 0.157%

    No Known Activations