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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior experience or previous roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zd
    -0.14
     memberId
    -0.14
    irit
    -0.13
    sembly
    -0.13
    keterangan
    -0.13
     WaitForSeconds
    -0.13
    stad
    -0.13
    aln
    -0.13
    orum
    -0.13
    ane
    -0.13
    POSITIVE LOGITS
     joining
    0.24
     Join
    0.23
     join
    0.20
    Join
    0.20
    joining
    0.19
     assuming
    0.19
    join
    0.18
     joined
    0.18
    .join
    0.18
     academia
    0.17
    Act Density 0.019%

    No Known Activations