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

    Neuronpedia

    INDEX
    Explanations

    references to bombs or explosive devices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceae
    -0.17
    edb
    -0.15
     vitae
    -0.14
    hire
    -0.14
    lify
    -0.14
    yte
    -0.14
    è¯ī
    -0.14
    lies
    -0.14
    OF
    -0.14
    à¥Ģस
    -0.14
    POSITIVE LOGITS
    shell
    0.43
    arded
    0.35
    astic
    0.32
    arding
    0.32
    ard
    0.30
    astically
    0.26
    adier
    0.26
     shell
    0.24
     disposal
    0.24
    ast
    0.24
    Act Density 0.010%

    No Known Activations