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

    Neuronpedia

    INDEX
    Explanations

    references to activities or events taking place on the streets

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of streets or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.78
    odka
    -0.77
    emis
    -0.70
    rang
    -0.70
     %%
    -0.69
    poon
    -0.67
    bass
    -0.67
    hemy
    -0.67
     Sorceress
    -0.67
    >(
    -0.66
    POSITIVE LOGITS
     lieu
    0.89
     Geneva
    0.82
     anticipation
    0.82
     Philadelphia
    0.81
     regards
    0.79
     Switzerland
    0.79
     Cannes
    0.79
     Dublin
    0.79
     Ci
    0.79
     vitro
    0.78
    Act Density 0.415%

    No Known Activations