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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idis
    -0.18
    ipers
    -0.17
    ernen
    -0.16
    agan
    -0.15
    swick
    -0.14
    avorites
    -0.14
    -Origin
    -0.14
    ÄIJT
    -0.14
    gro
    -0.14
     Gast
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.14
    tems
    0.14
    Inline
    0.14
     nett
    0.14
    Leap
    0.13
     Ire
    0.13
     Trojan
    0.13
     net
    0.13
    ething
    0.13
     dame
    0.13
    Act Density 0.076%

    No Known Activations