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

    Neuronpedia

    INDEX
    Explanations

    words related to endings and conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.23
    eru
    -0.20
    erate
    -0.19
    quez
    -0.18
    erot
    -0.18
    ambre
    -0.16
    ETY
    -0.16
    cona
    -0.16
    erin
    -0.16
    oine
    -0.15
    POSITIVE LOGITS
    y
    0.23
    ocrine
    0.22
    <|begin_of_text|>
    0.20
    ele
    0.19
    rick
    0.19
    eb
    0.19
    ell
    0.18
    eh
    0.18
    all
    0.17
    ahl
    0.17
    Act Density 0.022%

    No Known Activations