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

    Neuronpedia

    INDEX
    Explanations

    phrases incorporating the word "Based."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a basis or foundational concept for statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recess
    -0.79
    tons
    -0.76
     ever
    -0.72
     pleasure
    -0.71
     snag
    -0.68
     miss
    -0.64
     eternity
    -0.63
    loe
    -0.63
     spoil
    -0.63
    livion
    -0.62
    POSITIVE LOGITS
     Based
    3.51
    Based
    2.18
     based
    1.66
    based
    1.40
     Inspired
    1.16
     Depending
    1.14
     Given
    1.14
     According
    1.14
     Specifically
    1.12
     Using
    1.11
    Act Density 0.006%

    No Known Activations