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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "promise" and related forms, indicating discussions about commitments or guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrant
    -0.15
    enal
    -0.15
    rale
    -0.15
    боÑĢа
    -0.15
    sur
    -0.14
    alam
    -0.14
    remen
    -0.14
    ILD
    -0.14
    akk
    -0.14
    IRST
    -0.14
    POSITIVE LOGITS
     never
    0.21
    ably
    0.20
     delivery
    0.20
    /prom
    0.20
    ingly
    0.19
    /th
    0.17
     Never
    0.17
    never
    0.16
    Never
    0.16
     Delivery
    0.16
    Act Density 0.041%

    No Known Activations