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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or awareness of specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.18
    iasco
    -0.17
    ids
    -0.17
    dk
    -0.15
    ero
    -0.15
    go
    -0.15
    /ts
    -0.15
    role
    -0.14
     cigaret
    -0.14
    guard
    -0.14
    POSITIVE LOGITS
    æĻĵ
    0.23
    s
    0.23
    ledge
    0.21
    sand
    0.20
    ledged
    0.20
    -how
    0.20
    ingly
    0.19
    led
    0.18
    ledger
    0.18
     fact
    0.18
    Act Density 0.033%

    No Known Activations