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

    Neuronpedia

    INDEX
    Explanations

    themes related to personal identity and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¾ãģļ
    -0.15
    ãĥ¼ãĥĬ
    -0.14
    ppo
    -0.14
     Already
    -0.14
    loi
    -0.14
    ãĥ«ãĥķ
    -0.14
    átka
    -0.14
    ÅĽcie
    -0.14
    ëħĦëıĦ
    -0.14
    åħ¸
    -0.13
    POSITIVE LOGITS
     sometimes
    1.16
     occasionally
    0.99
    sometimes
    0.98
     Sometimes
    0.91
    Sometimes
    0.87
    ometimes
    0.75
     occasional
    0.75
     Occasionally
    0.75
     иногда
    0.74
     often
    0.63
    Act Density 1.165%

    No Known Activations