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

    Neuronpedia

    INDEX
    Explanations

    actions and qualities associated with interpersonal relationships and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    portion
    -0.14
    ipay
    -0.13
    .fast
    -0.13
    åIJĪæł¼
    -0.13
    ç´ł
    -0.13
    ãĤ»ãĥ³
    -0.13
    erialized
    -0.13
     Addition
    -0.13
    lessly
    -0.13
    OperationException
    -0.13
    POSITIVE LOGITS
     again
    0.19
    again
    0.18
     repeatedly
    0.18
     often
    0.17
     internally
    0.17
     makes
    0.17
     assoc
    0.17
     oft
    0.16
     make
    0.16
     frequently
    0.16
    Act Density 0.077%

    No Known Activations