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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to professional titles and roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĥ
    -0.17
    ifu
    -0.15
    çī©
    -0.15
    866
    -0.15
    VEC
    -0.14
    .uc
    -0.14
    ogene
    -0.14
    ilden
    -0.14
    dash
    -0.14
    bilder
    -0.14
    POSITIVE LOGITS
     agency
    0.41
     Agency
    0.38
     agencies
    0.37
    Agency
    0.37
    agency
    0.35
     Agencies
    0.35
     creative
    0.30
    creative
    0.30
     Creative
    0.28
     ad
    0.27
    Act Density 0.156%

    No Known Activations