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

    Neuronpedia

    INDEX
    Explanations

    references to emotional and ethical dilemmas involving relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ế
    -0.16
     bout
    -0.15
    culus
    -0.15
    outil
    -0.15
    atural
    -0.14
    mers
    -0.14
    verts
    -0.14
    isel
    -0.14
    ucs
    -0.14
    ersions
    -0.14
    POSITIVE LOGITS
     sensitive
    0.17
    ä¹ĥ
    0.15
    -sensitive
    0.15
    ÏĨοÏģ
    0.15
     ört
    0.15
    è¾
    0.14
    dol
    0.14
     Entr
    0.14
    bz
    0.14
    gren
    0.14
    Act Density 0.269%

    No Known Activations