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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating persistence or continuation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤıãģij
    -0.14
     nameof
    -0.13
     nearest
    -0.13
     вмÑĸ
    -0.13
    586
    -0.13
    omore
    -0.13
    rop
    -0.13
    686
    -0.13
     reservoir
    -0.12
    077
    -0.12
    POSITIVE LOGITS
     stay
    1.14
     Stay
    1.05
     stays
    1.04
     stayed
    1.03
    stay
    1.00
    Stay
    1.00
     staying
    0.99
     remain
    0.69
     remained
    0.69
     remains
    0.58
    Act Density 0.264%

    No Known Activations