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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific moments in time or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŃĨ
    -0.15
    erty
    -0.15
     ÙĨÙģ
    -0.14
    оÑĢи
    -0.14
    ignet
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    uckle
    -0.14
    å¥
    -0.14
    ãģ¾ãģł
    -0.14
    å¼Ħ
    -0.14
    POSITIVE LOGITS
    upon
    0.18
    rof
    0.15
     during
    0.14
    ovich
    0.14
     they
    0.14
    soever
    0.14
    ymm
    0.13
    å¦
    0.13
     she
    0.13
     began
    0.13
    Act Density 0.063%

    No Known Activations