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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to births and origins

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their places of birth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.81
    phasis
    -0.81
    olicy
    -0.79
    qqa
    -0.76
    alach
    -0.74
     eleph
    -0.69
    pty
    -0.69
    umbledore
    -0.68
    chnology
    -0.67
    arty
    -0.66
    POSITIVE LOGITS
    born
    1.12
    ness
    1.07
    nesses
    1.05
    lings
    0.94
    tons
    0.74
    smith
    0.73
    stellar
    0.73
    ling
    0.73
    stown
    0.70
    liness
    0.70
    Act Density 0.014%

    No Known Activations