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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing insistence or a strong need for adherence to certain ideas or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erk
    -0.17
    er
    -0.16
    isma
    -0.15
    wan
    -0.15
    bud
    -0.15
     chained
    -0.14
    -thirds
    -0.14
    rey
    -0.14
    oret
    -0.14
    erin
    -0.14
    POSITIVE LOGITS
    ently
    0.36
     upon
    0.32
    ively
    0.26
     Upon
    0.25
    Upon
    0.23
    ingly
    0.18
    upon
    0.18
    antly
    0.18
    entially
    0.17
    /request
    0.17
    Act Density 0.010%

    No Known Activations