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

    Neuronpedia

    INDEX
    Explanations

    terminology related to tightness or constriction in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     esser
    -0.73
    wpdb
    -0.71
    Pel
    -0.65
     pel
    -0.64
     Holbrook
    -0.64
     Marcell
    -0.63
    TabIndex
    -0.63
    Dakota
    -0.63
     Cardano
    -0.62
    Ger
    -0.61
    POSITIVE LOGITS
    Tight
    1.70
     tight
    1.66
     Tight
    1.66
    tight
    1.58
     tightness
    1.41
     tightly
    1.39
     tighter
    1.34
     tighten
    1.24
     tightened
    1.20
     tightening
    1.12
    Act Density 0.010%

    No Known Activations