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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and variables associated with data structures or algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.19
    roads
    -0.16
    c
    -0.15
    ound
    -0.15
    izz
    -0.15
    opa
    -0.15
    act
    -0.15
    atch
    -0.14
    l
    -0.14
    w
    -0.14
    POSITIVE LOGITS
    ahat
    0.18
    ILLA
    0.18
    sek
    0.17
    ovich
    0.15
    iyel
    0.15
    illa
    0.15
    оÑĤи
    0.15
    tlement
    0.15
    otten
    0.14
    HING
    0.14
    Act Density 0.159%

    No Known Activations