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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to interpersonal relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ->___
    -0.17
     weiber
    -0.17
    uitka
    -0.17
    ongo
    -0.17
    TRGL
    -0.16
    енÑĤÑĥ
    -0.16
     rumpe
    -0.16
    uzey
    -0.16
    Uvs
    -0.15
    IFn
    -0.15
    POSITIVE LOGITS
     hi
    0.20
     theme
    0.19
     hin
    0.18
     hem
    0.18
     us
    0.18
     themselves
    0.17
     themes
    0.17
    -h
    0.17
    'h
    0.16
    erial
    0.16
    Act Density 0.210%

    No Known Activations