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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to policies and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tracce
    -0.65
    CreateModel
    -0.65
     AssemblyCompany
    -0.61
    SerializedSize
    -0.54
    dropIfExists
    -0.54
    ValueStyle
    -0.54
     Convolution
    -0.53
     repul
    -0.51
     sóc
    -0.51
     PackageManager
    -0.50
    POSITIVE LOGITS
     unwise
    0.92
     imprud
    0.78
     foolish
    0.76
    estacks
    0.65
     stupidly
    0.63
    fjspx
    0.61
     recklessly
    0.60
     mistakes
    0.59
     mistake
    0.59
     folly
    0.59
    Act Density 0.461%

    No Known Activations