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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or theoretical concepts, particularly in relation to complex ideas or models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UIL
    -0.17
    uae
    -0.15
    cip
    -0.15
     Helm
    -0.14
    iggins
    -0.14
    ocaust
    -0.14
    iform
    -0.14
    ocre
    -0.13
    ancel
    -0.13
    abo
    -0.13
    POSITIVE LOGITS
     MSS
    0.24
     Yuk
    0.22
     Frog
    0.22
     Pat
    0.20
     SM
    0.20
     gauge
    0.20
     flipped
    0.20
     flav
    0.20
     Randall
    0.20
    textures
    0.19
    Act Density 0.006%

    No Known Activations