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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction and annihilation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeitige
    -0.83
    httphttps
    -0.74
    tableFuture
    -0.73
    geblich
    -0.69
    قایناق‌لار
    -0.69
    ThroughAttribute
    -0.68
    >{@
    -0.68
     oignon
    -0.67
     armis
    -0.65
     doulou
    -0.65
    POSITIVE LOGITS
    estroying
    1.21
     destruction
    1.16
     Destroy
    1.16
    Destroy
    1.14
    DESTROY
    1.10
     destroy
    1.09
     Destruction
    1.09
     destru
    1.02
     destroyed
    1.02
     destroys
    1.00
    Act Density 0.228%

    No Known Activations