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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to destruction or damaging actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.56
     culturelles
    -0.55
    gyz
    -0.54
     alimentaire
    -0.54
    stateProvider
    -0.53
    ыгана
    -0.52
    antMatchers
    -0.52
    Tikang
    -0.51
    calaureate
    -0.50
     devaient
    -0.50
    POSITIVE LOGITS
    estroying
    1.06
    DESTROY
    0.89
     destru
    0.88
     Destroy
    0.87
     destroyed
    0.87
     destroy
    0.86
    tructive
    0.82
     destroying
    0.81
    ChildScrollView
    0.81
    Destroy
    0.81
    Act Density 0.229%

    No Known Activations