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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes and confirmations in processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abi
    -0.19
    ansi
    -0.16
    bj
    -0.15
    kich
    -0.15
    elas
    -0.14
    strict
    -0.14
    orton
    -0.14
    ands
    -0.13
    onica
    -0.13
    lists
    -0.13
    POSITIVE LOGITS
     changes
    0.22
    changes
    0.18
     update
    0.18
     Changes
    0.17
    zar
    0.17
     immediately
    0.16
    Changes
    0.16
     reflected
    0.16
    ĶåĽŀ
    0.16
     updates
    0.16
    Act Density 0.026%

    No Known Activations