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

    Neuronpedia

    INDEX
    Explanations

    descriptions of tightness and sealing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     softened
    -0.14
    rax
    -0.14
     Sab
    -0.13
    825
    -0.13
    jang
    -0.13
    Transparent
    -0.13
    arsi
    -0.13
     calming
    -0.13
     Det
    -0.13
    ars
    -0.13
    POSITIVE LOGITS
     tight
    0.66
    tight
    0.55
     Tight
    0.55
     tighter
    0.52
     tighten
    0.42
     tightened
    0.42
     tightly
    0.40
    ç´§
    0.38
     tightening
    0.37
     firm
    0.36
    Act Density 0.177%

    No Known Activations