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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to tightness or being tightly constrained

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.54
    isissez
    -0.54
    parsedMessage
    -0.53
     Gefang
    -0.52
     CascadeType
    -0.50
     utafitiHapana
    -0.50
    хіво
    -0.50
    styleType
    -0.49
    -0.49
    EndGlobalSection
    -0.48
    POSITIVE LOGITS
     tight
    0.92
     Loose
    0.89
     loose
    0.86
    Loose
    0.85
     Tight
    0.81
    loose
    0.81
     hypothesis
    0.79
    Tight
    0.78
     sympath
    0.75
     sympathi
    0.75
    Act Density 0.193%

    No Known Activations