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

    Neuronpedia

    INDEX
    Explanations

    specific locations, such as streets, highways, and lands

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.68
    escription
    -0.67
     anat
    -0.67
    laus
    -0.65
    ensibly
    -0.65
    ilde
    -0.64
    earchers
    -0.63
    anson
    -0.63
     redacted
    -0.62
    olver
    -0.59
    POSITIVE LOGITS
     occasions
    0.89
     periphery
    0.77
     doorstep
    0.76
     behalf
    0.71
     alone
    0.70
     heels
    0.70
    tops
    0.66
     overlooking
    0.66
     occasion
    0.66
    çľ
    0.64
    Act Density 0.381%

    No Known Activations