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

    Neuronpedia

    INDEX
    Explanations

    words relating to significant changes or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.16
    onen
    -0.16
    ENU
    -0.16
    ooth
    -0.14
    lessness
    -0.14
    illus
    -0.14
    pla
    -0.14
    ty
    -0.14
     Rust
    -0.13
    .digest
    -0.13
    POSITIVE LOGITS
    çĬ
    0.16
    ereo
    0.15
    uja
    0.15
    uj
    0.14
     strides
    0.14
    657
    0.14
     Prescott
    0.14
    ียà¸Ķ
    0.14
    ITTER
    0.14
     Äįlán
    0.13
    Act Density 0.363%

    No Known Activations