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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases related to specific roles, positions, and achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLUS
    -0.17
     ensuite
    -0.17
    plus
    -0.15
     plus
    -0.15
     combined
    -0.15
    esp
    -0.14
    _DOM
    -0.14
     throughout
    -0.14
    Ð
    -0.14
    yst
    -0.13
    POSITIVE LOGITS
     following
    0.45
    following
    0.41
     after
    0.41
     having
    0.33
    after
    0.33
     Following
    0.31
    having
    0.31
    Following
    0.31
     dopo
    0.29
     ahead
    0.28
    Act Density 0.018%

    No Known Activations