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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quin
    -0.16
    gi
    -0.15
     Bale
    -0.14
    yle
    -0.14
    elier
    -0.14
    ettle
    -0.14
    /out
    -0.14
    oints
    -0.14
    oint
    -0.13
    este
    -0.13
    POSITIVE LOGITS
     Destroy
    0.16
    ively
    0.16
    æİī
    0.16
     havoc
    0.16
    ive
    0.15
    iveness
    0.15
    urgeon
    0.15
    .Destroy
    0.15
     destroy
    0.15
    Destroy
    0.15
    Act Density 0.041%

    No Known Activations