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

    Neuronpedia

    INDEX
    Explanations

    references to tightness or snugness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Katz
    -0.71
    TabIndex
    -0.68
    Ol
    -0.66
    trino
    -0.60
    Pel
    -0.60
     pel
    -0.60
    [:,
    -0.59
     متعلقه
    -0.58
    ForeColor
    -0.58
     Num
    -0.57
    POSITIVE LOGITS
     tight
    2.33
     Tight
    2.27
    Tight
    2.17
    tight
    2.08
     tighter
    1.96
     tighten
    1.77
     tightness
    1.75
     tightly
    1.74
     tightened
    1.70
     tightening
    1.63
    Act Density 0.124%

    No Known Activations