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

    Neuronpedia

    INDEX
    Explanations

    phrases related to successful outcomes and winning situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kit
    -0.15
     bond
    -0.15
    à¹ģà¸ľ
    -0.15
     пеÑĢег
    -0.14
    mos
    -0.14
    pta
    -0.14
     absorbing
    -0.14
    qid
    -0.14
    _swap
    -0.13
    anka
    -0.13
    POSITIVE LOGITS
     spin
    0.26
     landing
    0.25
     Landing
    0.24
     Spin
    0.24
     landed
    0.23
     spun
    0.23
     Award
    0.22
     awarded
    0.22
     spinning
    0.22
    .spin
    0.22
    Act Density 0.011%

    No Known Activations