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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persistence or remaining in a certain state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ello
    -0.73
     Dickerson
    -0.72
    Richards
    -0.71
    icu
    -0.68
    icos
    -0.67
     zod
    -0.65
    ici
    -0.64
    pf
    -0.64
    modelName
    -0.64
     cib
    -0.63
    POSITIVE LOGITS
    stay
    2.32
     stay
    2.29
     Stay
    2.13
    Stay
    2.08
    STAY
    2.07
     STAY
    2.02
     stays
    2.00
     stayed
    1.99
     staying
    1.95
     Staying
    1.94
    Act Density 0.129%

    No Known Activations