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

    Neuronpedia

    INDEX
    Explanations

    ZIP codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or identifiers related to geographical or organizational references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    waves
    -0.75
    undai
    -0.74
    raltar
    -0.72
    reach
    -0.71
    rir
    -0.71
    ularity
    -0.68
    perm
    -0.67
    heed
    -0.66
    elman
    -0.64
    entry
    -0.64
    POSITIVE LOGITS
    00
    1.01
    50
    0.85
    345
    0.79
    ¢
    0.75
     MPG
    0.74
     Commando
    0.74
    %
    0.74
    00000
    0.73
    80
    0.73
    %-
    0.73
    Act Density 0.058%

    No Known Activations