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

    Neuronpedia

    INDEX
    Explanations

    words related to breaking, destruction, or failure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction or breaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ature
    -0.75
    izations
    -0.74
    tarians
    -0.72
    uters
    -0.70
     inference
    -0.69
    oaded
    -0.68
    FactoryReloaded
    -0.67
    pmwiki
    -0.66
    iked
    -0.65
    abet
    -0.64
    POSITIVE LOGITS
    stal
    0.97
    stals
    0.87
    ãĤ©
    0.84
     shards
    0.79
     Shards
    0.78
     illusions
    0.76
     shattered
    0.76
     shatter
    0.74
    blue
    0.73
    IRE
    0.72
    Act Density 0.017%

    No Known Activations