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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or words related to geographical places

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific location, particularly "Rotterdam"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELS
    -0.70
    uncture
    -0.66
    ¬¼
    -0.63
    ï¸
    -0.63
     disparate
    -0.61
     undermin
    -0.60
    UTERS
    -0.59
    olulu
    -0.58
    cean
    -0.58
    ा
    -0.58
    POSITIVE LOGITS
    geist
    1.33
    ranean
    1.10
    rors
    1.01
    rible
    0.99
    tainment
    0.97
    rane
    0.93
    flies
    0.90
    ribly
    0.89
    restrial
    0.86
    gom
    0.86
    Act Density 0.036%

    No Known Activations