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

    Neuronpedia

    INDEX
    Explanations

    words related to caregiving and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tasted
    -0.15
     discussed
    -0.14
     onRequest
    -0.14
    ibel
    -0.14
     setattr
    -0.14
    ataka
    -0.14
     heard
    -0.13
    entin
    -0.13
     hrom
    -0.13
    zon
    -0.13
    POSITIVE LOGITS
     remembered
    0.28
     recall
    0.26
     recalled
    0.26
    recall
    0.25
    remember
    0.25
    _recall
    0.25
     remember
    0.25
     Recall
    0.25
     memories
    0.24
     Remember
    0.24
    Act Density 0.014%

    No Known Activations