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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of California and its cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foot
    -0.71
     Crimean
    -0.69
    theless
    -0.63
     pointers
    -0.63
    buster
    -0.60
     caution
    -0.59
     tre
    -0.59
     bumper
    -0.58
     rule
    -0.57
    ãĥĬ
    -0.57
    POSITIVE LOGITS
    .,
    1.62
    .;
    1.27
    .:
    1.12
    .?
    1.11
    ./
    1.05
    essee
    1.01
    adelphia
    1.01
    .,"
    0.98
    .),
    0.96
    .—
    0.96
    Act Density 0.036%

    No Known Activations