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

    Neuronpedia

    INDEX
    Explanations

    specific terms associated with structured planning and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.15
    ank
    -0.15
    ois
    -0.15
    ospace
    -0.15
    ipp
    -0.15
    erra
    -0.14
    aggi
    -0.13
    -alist
    -0.13
    yle
    -0.13
    æ§
    -0.13
    POSITIVE LOGITS
     there
    0.33
    there
    0.23
     we
    0.22
    æĿ¥è¯´
    0.21
     THERE
    0.20
     they
    0.19
     ÙģØ¥ÙĨ
    0.19
     it
    0.18
     thì
    0.18
     ÙĩÙĨاÙĥ
    0.17
    Act Density 0.364%

    No Known Activations