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

    Neuronpedia

    INDEX
    Explanations

    phrases related to development or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to development and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzi
    -0.75
    wered
    -0.72
    lua
    -0.71
    que
    -0.71
    yes
    -0.70
    wa
    -0.69
    duty
    -0.68
    clock
    -0.68
    bia
    -0.67
    dos
    -0.67
    POSITIVE LOGITS
    iates
    0.85
    iating
    0.84
    iator
    0.80
    urally
    0.78
    mental
    0.73
    developed
    0.72
    irtual
    0.70
    iated
    0.69
     partnerships
    0.68
    ivism
    0.67
    Act Density 0.048%

    No Known Activations