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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coding and programming reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.66
     leaſt
    -0.57
    __":
    -0.54
     }}$}
    -0.54
    writeField
    -0.54
    .")
    -0.52
    .’’
    -0.50
     ſte
    -0.50
    .",
    -0.49
    ✨:
    -0.48
    POSITIVE LOGITS
     manually
    0.79
     somehow
    0.74
     dynamically
    0.70
     correctly
    0.68
     incorrectly
    0.64
     internally
    0.60
     Somehow
    0.59
    Somehow
    0.57
     automatically
    0.56
     referenced
    0.56
    Act Density 2.093%

    No Known Activations