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

    Neuronpedia

    INDEX
    Explanations

    phrases involving negation or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sov
    -0.16
    ieux
    -0.15
    eva
    -0.15
    wy
    -0.15
    wan
    -0.15
    ries
    -0.15
    aeper
    -0.14
    ÙĤÙĤ
    -0.14
    hazi
    -0.14
    geois
    -0.14
    POSITIVE LOGITS
    oundary
    0.15
    ãģĺ
    0.14
    ject
    0.14
    UpdatedAt
    0.14
    NavItem
    0.14
    립
    0.14
    dfd
    0.13
     penal
    0.13
     Blades
    0.13
    اÛĮر
    0.13
    Act Density 0.082%

    No Known Activations