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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commitments and long-term relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htar
    -0.15
    noch
    -0.14
     bekl
    -0.14
    ä¸ĢåĪĩ
    -0.14
    aso
    -0.14
    å½
    -0.14
    æºĢ
    -0.14
     Couch
    -0.14
    pek
    -0.14
    ÑĢави
    -0.14
    POSITIVE LOGITS
    stable
    0.21
     stability
    0.21
     stable
    0.20
     longer
    0.19
     perman
    0.18
     Stability
    0.18
     continuity
    0.18
     Stable
    0.18
     amort
    0.17
    steady
    0.17
    Act Density 0.159%

    No Known Activations