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

    Neuronpedia

    INDEX
    Explanations

    words related to being captivated or captivating

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "captivate" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.70
     Integrity
    -0.68
     partnership
    -0.67
     Workers
    -0.65
     Enterprise
    -0.65
     trust
    -0.64
     Worker
    -0.64
    ukemia
    -0.64
    ãĤ§
    -0.64
     Pax
    -0.63
    POSITIVE LOGITS
    ivating
    1.12
    ivated
    1.02
    aining
    1.01
    ained
    1.00
    anted
    0.99
    icol
    0.94
    aning
    0.88
    anting
    0.86
    ains
    0.86
    iors
    0.86
    Act Density 0.017%

    No Known Activations