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

    Neuronpedia

    INDEX
    Explanations

    instances of promises and commitments made in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bios
    -0.16
    ilm
    -0.15
    ild
    -0.15
    vez
    -0.15
    -scale
    -0.15
    oster
    -0.14
     falta
    -0.13
    uby
    -0.13
    ijo
    -0.13
    rale
    -0.13
    POSITIVE LOGITS
    /prom
    0.20
     promises
    0.18
    ipple
    0.16
     promise
    0.16
    ingly
    0.14
    toInt
    0.14
    anges
    0.14
    AndGet
    0.14
    ment
    0.14
    tails
    0.14
    Act Density 0.041%

    No Known Activations