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

    Neuronpedia

    INDEX
    Explanations

    requests for clarity or specificity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aru
    -0.15
    ãĥ³ãĤ°ãĥ«
    -0.14
    .learn
    -0.14
    orgen
    -0.14
     Composite
    -0.14
    огод
    -0.14
    ÄįenÃŃ
    -0.14
    akis
    -0.14
    Composite
    -0.14
    557
    -0.14
    POSITIVE LOGITS
     block
    0.31
     blocks
    0.31
     blocked
    0.29
    -block
    0.29
     Blocks
    0.28
     Block
    0.28
    blocks
    0.28
    BLOCK
    0.27
    Blocks
    0.27
     bloque
    0.27
    Act Density 0.031%

    No Known Activations