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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oint
    -0.16
    ford
    -0.16
    ji
    -0.15
    assy
    -0.15
    /out
    -0.14
    gesi
    -0.14
    AndPassword
    -0.14
    stral
    -0.14
    cum
    -0.14
    jet
    -0.14
    POSITIVE LOGITS
     havoc
    0.18
    lijk
    0.17
    ively
    0.17
    /update
    0.17
    swer
    0.16
    æİī
    0.16
    urgeon
    0.16
    ive
    0.16
    edException
    0.15
    à¥įण
    0.15
    Act Density 0.056%

    No Known Activations