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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acceptance and consequences in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    richt
    -0.18
    ynet
    -0.14
    argar
    -0.14
    agine
    -0.14
    WAY
    -0.14
    erson
    -0.13
    alist
    -0.13
     Aquarium
    -0.13
    ullet
    -0.13
    linky
    -0.13
    POSITIVE LOGITS
    nesc
    0.17
     backed
    0.14
    误
    0.14
     indeb
    0.14
    tsky
    0.14
    rava
    0.14
    dik
    0.13
     tout
    0.13
     Ru
    0.13
     leg
    0.13
    Act Density 0.586%

    No Known Activations