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

    Neuronpedia

    INDEX
    Explanations

    references to significant disasters or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ąt
    -0.47
    efeller
    -0.45
    cleo
    -0.45
     كومونز
    -0.45
     bienvenue
    -0.44
    Exit
    -0.44
     assolutamente
    -0.44
     kalian
    -0.43
     consuls
    -0.43
    ترة
    -0.42
    POSITIVE LOGITS
     wildfires
    0.79
     ravaged
    0.78
    AndEndTag
    0.77
     fires
    0.76
    fires
    0.75
    DAMAGE
    0.72
     wildfire
    0.71
     devastation
    0.69
     floods
    0.69
    IUrlHelper
    0.69
    Act Density 0.425%

    No Known Activations