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

    Neuronpedia

    INDEX
    Explanations

    words related to specific geographical locations, particularly towns or cities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "aun" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.72
     horm
    -0.62
     MPG
    -0.60
    IDA
    -0.60
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.59
    ONS
    -0.59
    EM
    -0.59
    FT
    -0.58
     sands
    -0.58
     Quantum
    -0.58
    POSITIVE LOGITS
    eers
    0.98
    eer
    0.96
    cheon
    0.94
    gha
    0.93
    erate
    0.91
    emouth
    0.89
    thood
    0.89
    tesy
    0.88
    unci
    0.88
    gement
    0.86
    Act Density 0.042%

    No Known Activations