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

    Neuronpedia

    INDEX
    Explanations

    phrases related to development and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the development of projects or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzi
    -0.80
    dos
    -0.74
    que
    -0.72
    yes
    -0.71
    wered
    -0.70
    nea
    -0.68
    please
    -0.68
    tery
    -0.68
    duty
    -0.67
    beck
    -0.66
    POSITIVE LOGITS
    iating
    0.84
    iates
    0.83
    iator
    0.80
    mental
    0.77
    iated
    0.75
    irtual
    0.73
    urally
    0.73
     prototypes
    0.71
     partnerships
    0.69
    schild
    0.68
    Act Density 0.047%

    No Known Activations