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

    Neuronpedia

    INDEX
    Explanations

    concepts related to blame and accountability in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.16
     ster
    -0.15
    ancellable
    -0.15
    ân
    -0.14
    ValueCollection
    -0.14
    ugh
    -0.14
    slack
    -0.14
     ims
    -0.14
    lán
    -0.14
    -scal
    -0.14
    POSITIVE LOGITS
    Gas
    0.21
     Gas
    0.21
     narciss
    0.20
     gas
    0.18
    gas
    0.18
     abuse
    0.18
     íĶ¼íķ´
    0.17
     manipulation
    0.17
     triang
    0.16
    ovny
    0.16
    Act Density 0.017%

    No Known Activations