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

    Neuronpedia

    INDEX
    Explanations

    references to fences or fencing around an area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fence, fenced, or fencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UA
    -0.60
     Mia
    -0.53
     AAA
    -0.51
     Schmid
    -0.50
     Diar
    -0.50
     Gottlieb
    -0.50
    __*/
    -0.49
     AA
    -0.47
     Bryan
    -0.47
     RIA
    -0.46
    POSITIVE LOGITS
     Fence
    1.13
     fence
    1.09
    Fence
    1.06
     fences
    1.02
    fence
    1.01
     fencing
    0.93
     Fencing
    0.90
     fenced
    0.81
     plufieurs
    0.77
     ainfi
    0.72
    Act Density 0.005%

    No Known Activations