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

    Neuronpedia

    INDEX
    Explanations

    references to brokenness or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropa
    -0.16
    ousse
    -0.16
    (||
    -0.16
    çĦ¼
    -0.16
    rex
    -0.15
    rove
    -0.15
    gard
    -0.15
    _Execute
    -0.14
    rame
    -0.14
    CursorPosition
    -0.14
    POSITIVE LOGITS
     broken
    0.25
    -hearted
    0.24
    broken
    0.24
    Broken
    0.23
    heart
    0.23
    ess
    0.21
     Broken
    0.20
    -backed
    0.19
     shattered
    0.19
     broke
    0.18
    Act Density 0.018%

    No Known Activations