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

    Neuronpedia

    INDEX
    Explanations

    references to elevated locations and viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.58
     AssemblyTitle
    -0.57
    CodedInputStream
    -0.53
    )++;
    -0.51
    ParallelGroup
    -0.51
    NSYLVANIA
    -0.51
    ixas
    -0.47
    ldb
    -0.46
    gbaar
    -0.46
    nipeg
    -0.45
    POSITIVE LOGITS
     vantage
    0.86
     balcony
    0.75
     perched
    0.73
     overlooking
    0.69
     observation
    0.69
     Viewing
    0.67
     Observation
    0.66
     atop
    0.65
     viewing
    0.65
     Balcony
    0.65
    Act Density 0.172%

    No Known Activations