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

    Neuronpedia

    INDEX
    Explanations

    indicative phrases related to personal relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shouldBe
    -0.15
    apolis
    -0.15
    odon
    -0.13
    hled
    -0.13
     mænd
    -0.13
    aload
    -0.13
    oge
    -0.13
    Âĭ
    -0.13
    mouseleave
    -0.13
    agra
    -0.12
    POSITIVE LOGITS
     have
    0.72
     having
    0.72
     Have
    0.68
    æľī
    0.68
    having
    0.64
     had
    0.64
    Have
    0.64
    have
    0.63
     memiliki
    0.61
     æľī
    0.60
    Act Density 1.370%

    No Known Activations