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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duration or time frames in a person's life or career

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usan
    -0.14
    etti
    -0.14
    SEG
    -0.14
    .appspot
    -0.14
    kili
    -0.13
    SCII
    -0.13
     Immutable
    -0.13
    ritos
    -0.13
     resil
    -0.13
    _regularizer
    -0.13
    POSITIVE LOGITS
    arend
    0.18
    ãĥ«ãĥī
    0.15
    essen
    0.15
    539
    0.14
    spent
    0.14
    -append
    0.14
    union
    0.14
    rene
    0.14
    :@""
    0.14
    allet
    0.13
    Act Density 0.063%

    No Known Activations