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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chers
    -0.17
    pc
    -0.16
    antro
    -0.16
    izzo
    -0.16
    ersh
    -0.15
    plevel
    -0.14
    presso
    -0.14
    sj
    -0.14
    _OBS
    -0.14
    olls
    -0.14
    POSITIVE LOGITS
    -go
    0.37
     camper
    0.27
     endings
    0.25
     ending
    0.25
     Ending
    0.24
    -medium
    0.24
     hour
    0.23
     Hour
    0.23
     camp
    0.22
     Camp
    0.22
    Act Density 0.026%

    No Known Activations