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

    Neuronpedia

    INDEX
    Explanations

    terminology related to social issues and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptune
    -0.15
    quals
    -0.15
    enheim
    -0.15
    ung
    -0.14
     Doom
    -0.14
    uito
    -0.14
    ogr
    -0.14
    ãģĬãĤĬ
    -0.14
    ehr
    -0.14
    itters
    -0.14
    POSITIVE LOGITS
    izing
    0.22
    ized
    0.20
    aight
    0.20
    ising
    0.19
    ization
    0.19
     justice
    0.17
    ize
    0.17
     distancing
    0.17
    -economic
    0.16
    ware
    0.16
    Act Density 0.032%

    No Known Activations