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

    Neuronpedia

    INDEX
    Explanations

    geographical locations, particularly cities

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and mentions of cardboard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.81
    hower
    -0.77
    kaya
    -0.76
    odium
    -0.76
    nis
    -0.75
    orically
    -0.72
    nit
    -0.71
    ãĤ´ãĥ³
    -0.71
    mann
    -0.70
    hetically
    -0.70
    POSITIVE LOGITS
    ulla
    0.74
    berries
    0.72
    ãģ®éŃĶ
    0.69
    obyl
    0.68
     Chaser
    0.68
     Sco
    0.67
    STAR
    0.65
    é»Ĵ
    0.65
    Winged
    0.63
     bark
    0.63
    Act Density 0.024%

    No Known Activations