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

    Neuronpedia

    INDEX
    Explanations

    references to being "down" or having a negative sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.69
    IVEREF
    -0.64
    دانشنامهٔ
    -0.60
     betweenstory
    -0.57
    mits
    -0.56
    PhysRev
    -0.54
    InitVars
    -0.54
     Савезне
    -0.53
    bukkit
    -0.52
    DotNetBar
    -0.51
    POSITIVE LOGITS
    sizing
    0.81
    payment
    0.71
     payment
    0.69
    pour
    0.66
     syndrome
    0.64
    playing
    0.64
    sized
    0.62
    er
    0.62
     PAYMENT
    0.62
    GraphicsUnit
    0.61
    Act Density 0.160%

    No Known Activations