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

    Neuronpedia

    INDEX
    Explanations

    references to shows, episodes, or segments titled "On" or related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.18
    rias
    -0.16
    ople
    -0.15
    pos
    -0.15
    è¿«
    -0.15
    ear
    -0.15
    aram
    -0.14
    float
    -0.14
    ea
    -0.14
    .safe
    -0.14
    POSITIVE LOGITS
    ward
    0.23
    ions
    0.19
    WARD
    0.19
    ion
    0.18
    SCALL
    0.17
    egin
    0.17
     yer
    0.16
    assis
    0.16
    iones
    0.16
    .defineProperty
    0.16
    Act Density 0.034%

    No Known Activations