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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating ongoing or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    613
    -0.15
    amba
    -0.15
    arme
    -0.15
    askan
    -0.14
    run
    -0.14
    quate
    -0.14
    arna
    -0.14
    hawk
    -0.13
    rum
    -0.13
    ri
    -0.13
    POSITIVE LOGITS
    DDS
    0.16
    :\/\/
    0.15
     till
    0.15
    arily
    0.15
    ="{!!
    0.15
    aneous
    0.15
    ocal
    0.14
    aneously
    0.14
    _alive
    0.14
    ëĬĺ
    0.14
    Act Density 0.065%

    No Known Activations