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

    Neuronpedia

    INDEX
    Explanations

    references to humanity and its social constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _RS
    -0.15
    ias
    -0.15
    olley
    -0.15
    $MESS
    -0.15
     Ulus
    -0.14
    halb
    -0.14
    illow
    -0.14
    rikes
    -0.14
    ustum
    -0.14
    涨
    -0.14
    POSITIVE LOGITS
    ãĢģ
    0.15
    θÏħ
    0.15
     beings
    0.15
    849
    0.15
    otropic
    0.15
    149
    0.14
     adult
    0.14
    ิว
    0.14
    vider
    0.14
    âĨIJ
    0.14
    Act Density 0.101%

    No Known Activations