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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and landmarks in Manhattan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.21
    outer
    -0.19
    ellas
    -0.16
     Harr
    -0.16
    azon
    -0.16
    ikan
    -0.16
    #line
    -0.15
    agg
    -0.14
    æ²»
    -0.14
     Hil
    -0.14
    POSITIVE LOGITS
     Houston
    0.19
     Bow
    0.18
     Greenwich
    0.18
    istrovstvÃŃ
    0.18
    avar
    0.16
     bow
    0.15
    Reuse
    0.14
     Mercer
    0.14
    antha
    0.14
    ÏĦÏĤ
    0.14
    Act Density 0.076%

    No Known Activations