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

    Neuronpedia

    INDEX
    Explanations

    references to consistency or consensus in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    et
    -0.17
    ETS
    -0.17
     mime
    -0.14
    érica
    -0.14
    ç´ļ
    -0.14
    ets
    -0.14
    cheon
    -0.14
     Nó
    -0.14
    eb
    -0.14
    etting
    -0.14
    POSITIVE LOGITS
     cons
    0.50
     Cons
    0.45
    Cons
    0.40
    -cons
    0.38
    cons
    0.36
    .Cons
    0.34
    _cons
    0.34
     CONS
    0.31
     Kons
    0.31
    .cons
    0.30
    Act Density 0.012%

    No Known Activations