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

    Neuronpedia

    INDEX
    Explanations

    elements related to interpersonal relationships and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĬ
    -0.15
    ppo
    -0.15
    ãģ¾ãģļ
    -0.15
    yte
    -0.14
    ãĥ«ãĥķ
    -0.14
     долго
    -0.14
    ihan
    -0.14
    ownik
    -0.13
    átka
    -0.13
    åħ¸
    -0.13
    POSITIVE LOGITS
     sometimes
    1.09
     occasionally
    0.99
    sometimes
    0.92
     Sometimes
    0.85
    Sometimes
    0.82
     occasional
    0.78
     Occasionally
    0.74
     иногда
    0.72
    ometimes
    0.72
     ocas
    0.57
    Act Density 0.906%

    No Known Activations