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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    sentences containing forms of the verb "to be" and related auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.70
    bush
    -0.70
    hedon
    -0.66
    gom
    -0.65
    Fake
    -0.61
    ente
    -0.60
    conn
    -0.59
    )=(
    -0.58
    uctor
    -0.58
    bury
    -0.57
    POSITIVE LOGITS
     also
    1.43
     furthermore
    1.39
     moreover
    1.34
     therefore
    1.21
     additionally
    1.14
     however
    1.07
    also
    1.06
     meanwhile
    1.02
     then
    0.99
     thus
    0.96
    Act Density 0.481%

    No Known Activations