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

    Neuronpedia

    INDEX
    Explanations

    references to military installations or forts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Himo
    -0.97
     myſelf
    -0.88
     Efq
    -0.84
     pleaſure
    -0.81
     themſelves
    -0.79
     resourceCulture
    -0.78
     greateſt
    -0.78
     Theſe
    -0.78
     Majefty
    -0.75
    SBATCH
    -0.74
    POSITIVE LOGITS
     Fort
    0.66
     FORT
    0.54
     Worth
    0.53
     worth
    0.52
     Z
    0.52
    l
    0.52
    Fort
    0.51
    Worth
    0.50
     St
    0.49
    worth
    0.47
    Act Density 0.070%

    No Known Activations