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

    Neuronpedia

    INDEX
    Explanations

    emotional interactions and expressions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    211
    -0.15
     blindness
    -0.14
     Lars
    -0.14
    елик
    -0.14
    _APPS
    -0.14
    .isDefined
    -0.14
    umsuz
    -0.14
     Guidance
    -0.13
    ect
    -0.13
    pkg
    -0.13
    POSITIVE LOGITS
    adm
    0.16
    coder
    0.16
    leh
    0.15
    allery
    0.14
    olut
    0.14
    burgh
    0.14
    rror
    0.14
    ëł¹
    0.14
    pper
    0.14
     Düz
    0.14
    Act Density 0.077%

    No Known Activations