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

    Neuronpedia

    INDEX
    Explanations

    words related to pills or medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.25
    eties
    -0.20
    eme
    -0.19
    emu
    -0.18
    eer
    -0.18
    etes
    -0.18
    yne
    -0.18
    ely
    -0.18
    emed
    -0.17
    emp
    -0.17
    POSITIVE LOGITS
    iard
    0.32
    owy
    0.28
    ings
    0.27
    umin
    0.26
    iams
    0.26
    inois
    0.25
    iterate
    0.24
    l
    0.24
    ard
    0.24
    ows
    0.24
    Act Density 0.080%

    No Known Activations