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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decisive actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    replace
    -0.76
     Provides
    -0.72
    perse
    -0.71
    cé
    -0.71
    VERTISEMENT
    -0.67
    placed
    -0.65
    dro
    -0.64
    rand
    -0.63
    ternal
    -0.62
    ienne
    -0.62
    POSITIVE LOGITS
     brakes
    1.24
     proverbial
    1.14
     blame
    1.11
     slightest
    1.10
     same
    1.06
     entire
    1.04
     reins
    1.02
     curtain
    1.01
     envelope
    0.99
     entirety
    0.98
    Act Density 0.238%

    No Known Activations