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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to social issues and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ung
    -0.17
    iosa
    -0.15
     Doom
    -0.15
    .metamodel
    -0.15
    ogr
    -0.14
    aler
    -0.14
    enheim
    -0.14
    quals
    -0.14
     pii
    -0.14
    gers
    -0.14
    POSITIVE LOGITS
    izing
    0.19
    ized
    0.18
     justice
    0.18
    aight
    0.17
    ising
    0.16
    ÑĢин
    0.16
     distancing
    0.16
    ware
    0.16
    thane
    0.15
    istic
    0.15
    Act Density 0.039%

    No Known Activations