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

    Neuronpedia

    INDEX
    Explanations

    It seems that neuron 4 is looking for names or terms related to specific places or persons

    oai_token-act-pair · gpt-3.5-turbo

    single character tokens or names with specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.76
    APS
    -0.68
    BILITIES
    -0.62
    growth
    -0.61
    OTAL
    -0.59
    İĭ
    -0.58
    CLOSE
    -0.57
    lest
    -0.57
     somet
    -0.57
     rall
    -0.56
    POSITIVE LOGITS
    sted
    0.66
     Hospital
    0.65
     hybrids
    0.62
    heit
    0.62
    heid
    0.62
     combo
    0.61
     joint
    0.61
    ?????-
    0.60
    imore
    0.60
    enna
    0.59
    Act Density 0.284%

    No Known Activations