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

    Neuronpedia

    INDEX
    Explanations

    references to aggressive or violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lán
    -0.16
     cr
    -0.15
    .gwt
    -0.15
    aphrag
    -0.14
    "<?
    -0.14
    .sap
    -0.14
    bilt
    -0.14
     AppBundle
    -0.14
    icio
    -0.14
    atoi
    -0.14
    POSITIVE LOGITS
    robat
    0.15
    airs
    0.14
    ávÄĽ
    0.14
    .gdx
    0.14
    elerik
    0.14
    endant
    0.14
    жд
    0.13
     sooner
    0.13
    unsch
    0.13
    resher
    0.13
    Act Density 0.017%

    No Known Activations