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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persistence or continuity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "stay in" along with related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.78
    ĪĴ
    -0.75
    DragonMagazine
    -0.75
    ILLE
    -0.75
    irst
    -0.66
    estic
    -0.64
    essler
    -0.63
    elf
    -0.63
    ¶ħ
    -0.62
    Ĭ±
    -0.61
    POSITIVE LOGITS
     bounds
    0.89
    clud
    0.81
     indefinitely
    0.75
     quo
    0.72
     confines
    0.72
     situ
    0.70
    bound
    0.69
     haunt
    0.68
     obscurity
    0.68
    memory
    0.67
    Act Density 0.095%

    No Known Activations