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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "perform" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARD
    -0.15
    portun
    -0.14
    rox
    -0.14
    دار
    -0.14
    andler
    -0.14
    hunt
    -0.14
    roker
    -0.14
    .lazy
    -0.13
    еÑĢж
    -0.13
    ĽĦ
    -0.13
    POSITIVE LOGITS
     tasks
    0.24
     duties
    0.22
    Tasks
    0.19
     Tasks
    0.19
     feats
    0.18
    ä»»åĬ¡
    0.17
     actions
    0.17
    tasks
    0.16
    _tasks
    0.16
    inkel
    0.16
    Act Density 0.032%

    No Known Activations