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

    Neuronpedia

    INDEX
    Explanations

    mention of specific locations, particularly city names and related geographical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Figure
    -0.64
     Figure
    -0.63
    Geograf
    -0.51
    łam
    -0.50
    monary
    -0.49
    TES
    -0.48
    ctober
    -0.48
    OwnProperty
    -0.47
     Reverend
    -0.47
    }:{
    -0.46
    POSITIVE LOGITS
     Sept
    0.94
     Calif
    0.89
     Nov
    0.87
     Oct
    0.86
     Feb
    0.85
     Aug
    0.84
     Okla
    0.81
     Gov
    0.80
     Jan
    0.80
     Dec
    0.79
    Act Density 0.540%

    No Known Activations