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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    APPER
    -0.17
    AXB
    -0.15
    169
    -0.15
    Ñģи
    -0.14
    ãĥ»ãĥ»ãĥ»↵↵
    -0.14
    eway
    -0.14
    âĸį
    -0.14
    udos
    -0.14
    931
    -0.14
    POSITIVE LOGITS
    rr
    0.31
    www
    0.31
    tt
    0.28
    uu
    0.28
    nn
    0.27
    ss
    0.27
    ee
    0.27
    aa
    0.27
    ww
    0.26
    ii
    0.26
    Act Density 0.267%

    No Known Activations