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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aye
    -0.17
    otec
    -0.15
    odia
    -0.15
    agonal
    -0.15
    imore
    -0.15
    udi
    -0.14
    andalone
    -0.14
    compressed
    -0.13
    SharedPtr
    -0.13
    Äįka
    -0.13
    POSITIVE LOGITS
     about
    0.31
     whether
    0.24
     why
    0.24
     how
    0.22
     what
    0.21
     if
    0.21
    about
    0.20
     About
    0.19
     where
    0.19
    _about
    0.19
    Act Density 0.012%

    No Known Activations