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

    Neuronpedia

    INDEX
    Explanations

    terms related to software programming and structured data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.56
    @[+][
    -0.51
     coach
    -0.51
     mother
    -0.51
     father
    -0.48
     captain
    -0.48
     captains
    -0.48
    irmish
    -0.47
    igma
    -0.47
     governors
    -0.46
    POSITIVE LOGITS
     Writer
    0.91
    Writer
    0.88
     Researcher
    0.86
     Driver
    0.81
     Dancer
    0.81
     Leader
    0.81
     Player
    0.80
     Reporter
    0.80
     Reader
    0.80
     Teacher
    0.80
    Act Density 0.599%

    No Known Activations