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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating professional experience and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sst
    -0.16
    apid
    -0.16
    issent
    -0.15
    /from
    -0.15
    svc
    -0.14
    sse
    -0.13
    olon
    -0.13
    619
    -0.13
    کرÛĮ
    -0.13
     ActionTypes
    -0.13
    POSITIVE LOGITS
     experience
    0.31
    -ex
    0.28
    experience
    0.27
     expérience
    0.23
     Experience
    0.23
    Experience
    0.23
     experiencia
    0.22
    _experience
    0.22
     experi
    0.21
     experiences
    0.20
    Act Density 0.031%

    No Known Activations