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

    Neuronpedia

    INDEX
    Explanations

    references to various harmful substances and contaminants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.60
     autorytatywna
    -0.57
    CROSSTALK
    -0.47
    хьтан
    -0.46
     CommonModule
    -0.44
    AntiForgeryToken
    -0.44
    RTEX
    -0.43
    onResume
    -0.43
     kaarangay
    -0.43
    Lycka
    -0.43
    POSITIVE LOGITS
     contaminants
    0.36
     ſta
    0.35
     organ
    0.34
    awaiter
    0.34
     contamin
    0.33
    MenuGroup
    0.32
     substances
    0.32
     toxins
    0.31
     poisonous
    0.31
     conter
    0.31
    Act Density 0.040%

    No Known Activations