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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "initiate" and variations or related terms referring to initiatives or starting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.23
    lier
    -0.18
    ÑĤоÑĢ
    -0.18
    thing
    -0.18
    liness
    -0.17
    ìĦľëĬĶ
    -0.17
    /is
    -0.17
    IPH
    -0.17
    -0.16
    ness
    -0.15
    POSITIVE LOGITS
    iative
    0.28
    iate
    0.25
    iat
    0.24
    iator
    0.24
    iating
    0.23
    iation
    0.23
    iated
    0.23
    ital
    0.20
    ally
    0.20
    itial
    0.19
    Act Density 0.019%

    No Known Activations