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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for references to a specific location, "Long"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location, Long Island

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.77
    ħĭ
    -0.76
    istine
    -0.74
    onomic
    -0.74
    ãĥ¯
    -0.73
    irrel
    -0.73
    代
    -0.71
    tical
    -0.70
    ãĤ®
    -0.70
    opoulos
    -0.67
    POSITIVE LOGITS
    itudinal
    0.96
    shore
    0.86
    sword
    0.85
     corrid
    0.84
     Long
    0.81
    Long
    0.79
    itude
    0.79
    er
    0.79
    long
    0.79
    wind
    0.78
    Act Density 0.011%

    No Known Activations