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

    Neuronpedia

    INDEX
    Explanations

    locations and specific geographical references

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reply
    -0.71
     differently
    -0.66
     meantime
    -0.63
     backward
    -0.63
     ãĤµ
    -0.63
     McKin
    -0.62
     backwards
    -0.60
     Canaver
    -0.60
     uniquely
    -0.60
     nonex
    -0.58
    POSITIVE LOGITS
     horizon
    0.87
     sidx
    0.82
    antage
    0.78
     cliffs
    0.77
     axis
    0.76
    axis
    0.75
     entrance
    0.74
     residences
    0.73
    ramids
    0.73
     boundaries
    0.72
    Act Density 0.458%

    No Known Activations