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

    Neuronpedia

    INDEX
    Explanations

    references to emotional expressions and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.46
    RTEE
    -0.45
     :-(
    -0.44
    KommentareTeilen
    -0.44
     :-)
    -0.43
    Hmmmm
    -0.43
    IMHO
    -0.42
     ;-)
    -0.42
    Abitanti
    -0.42
    )‏
    -0.40
    POSITIVE LOGITS
    ScopeManager
    0.52
     LoggerFactory
    0.51
     incompar
    0.48
     cultivators
    0.47
    elemField
    0.46
     cultivation
    0.45
     gewöhn
    0.45
    DeleteMapping
    0.44
     Lý
    0.43
     dao
    0.43
    Act Density 0.110%

    No Known Activations