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

    Neuronpedia

    INDEX
    Explanations

    references to locations or vague places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.73
    n
    -0.73
    s
    -0.71
    m
    -0.70
    p
    -0.70
    b
    -0.69
    tis
    -0.68
    ps
    -0.67
     n
    -0.64
    f
    -0.64
    POSITIVE LOGITS
     somewhere
    2.64
     anywhere
    2.56
    somewhere
    2.54
    anywhere
    2.51
     Somewhere
    2.48
     Anywhere
    2.42
     nowhere
    2.37
    Somewhere
    2.26
     someplace
    2.24
    Anywhere
    2.21
    Act Density 0.038%

    No Known Activations