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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explosions or explosive devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldem
    -0.19
    ernals
    -0.16
    edor
    -0.15
    lify
    -0.15
    INF
    -0.15
    à¥Ģस
    -0.14
    ools
    -0.14
    Interpolator
    -0.14
     vitae
    -0.14
    yte
    -0.14
    POSITIVE LOGITS
    arded
    0.27
    shell
    0.27
    arding
    0.27
    astic
    0.20
    ard
    0.20
    (shell
    0.18
    ards
    0.18
    astically
    0.18
    adil
    0.17
     bomb
    0.17
    Act Density 0.016%

    No Known Activations