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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hani
    -0.18
    à¸ĵ
    -0.16
    uen
    -0.16
    мом
    -0.15
    ÑĪе
    -0.14
    ayment
    -0.14
    ê³
    -0.14
    ÑĪев
    -0.13
    аÑħ
    -0.13
    áy
    -0.13
    POSITIVE LOGITS
    eve
    0.17
    edin
    0.17
    obus
    0.16
     differently
    0.15
    quin
    0.15
     BLL
    0.15
    eyn
    0.15
    ews
    0.14
    UAL
    0.14
     hypothetical
    0.14
    Act Density 0.176%

    No Known Activations