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

    Neuronpedia

    INDEX
    Explanations

    expressions of care, concern, and acknowledgment in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reve
    -0.15
    nika
    -0.15
    probe
    -0.14
    urette
    -0.14
    yz
    -0.14
    lew
    -0.14
    ãĥ¼ãĤ¸
    -0.13
     Zug
    -0.13
     tel
    -0.13
    лив
    -0.13
    POSITIVE LOGITS
    бол
    0.17
     indeed
    0.16
    oud
    0.16
     cared
    0.15
     importance
    0.15
     cares
    0.15
    Ø´ÙħاÙĦÛĮ
    0.15
    ythe
    0.15
    oli
    0.14
    cip
    0.14
    Act Density 0.143%

    No Known Activations